@pydantic/genai-prices 0.0.66 → 0.0.67

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/dist/cli.js +3843 -1703
  2. package/dist/index.cjs +5 -5
  3. package/dist/index.js +3795 -1655
  4. package/package.json +1 -1
package/dist/index.cjs CHANGED
@@ -1,10 +1,10 @@
1
- "use strict";Object.defineProperty(exports,Symbol.toStringTag,{value:"Module"});const Q=[{id:"anthropic",name:"Anthropic",pricing_urls:["https://www.anthropic.com/pricing#api"],api_pattern:"https://api\\.anthropic\\.com",model_match:{contains:"claude"},provider_match:{contains:"anthropic"},extractors:[{api_flavor:"default",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:"cache_creation_input_tokens",dest:"input_tokens",required:!1},{path:"cache_read_input_tokens",dest:"input_tokens",required:!1},{path:"cache_creation_input_tokens",dest:"cache_write_tokens",required:!1},{path:"cache_read_input_tokens",dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:"cached_tokens",dest:"cache_read_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"claude-2",name:"Claude 2.0 / 2.1",description:`Claude 2 is Anthropic's previous generation model, offering reliable performance for various tasks. This includes Claude 2.0 and Claude 2.1.
2
- `,match:{or:[{starts_with:"claude-2"},{contains:"claude-v2"}]},context_window:2e5,prices:{input_mtok:8,output_mtok:24}},{id:"claude-3-5-haiku-latest",name:"Claude Haiku 3.5",description:"Fastest, most cost-effective model",match:{or:[{starts_with:"claude-3-5-haiku"},{starts_with:"claude-3.5-haiku"}]},context_window:2e5,prices:{input_mtok:.8,cache_write_mtok:1,cache_read_mtok:.08,output_mtok:4}},{id:"claude-3-5-sonnet",name:"Claude Sonnet 3.5",description:"Claude 3.5 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments.",match:{or:[{starts_with:"claude-3-5-sonnet"},{starts_with:"claude-3.5-sonnet"}]},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-3-7-sonnet-latest",name:"Claude Sonnet 3.7",description:"Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities.",match:{or:[{starts_with:"claude-3-7-sonnet"},{starts_with:"claude-3.7-sonnet"},{starts_with:"claude-sonnet-3.7"},{starts_with:"claude-sonnet-3-7"}]},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-3-haiku",name:"Claude Haiku 3",description:"Fastest, most cost-effective model",match:{starts_with:"claude-3-haiku"},context_window:2e5,prices:{input_mtok:.25,cache_write_mtok:.3,cache_read_mtok:.03,output_mtok:1.25}},{id:"claude-3-opus-latest",name:"Claude Opus 3",description:"Claude 3 Opus was Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding.",match:{starts_with:"claude-3-opus"},context_window:2e5,prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"claude-3-sonnet",name:"Claude 3 Sonnet",description:"Claude 3 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments.",match:{starts_with:"claude-3-sonnet"},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-fable-5",name:"Claude Fable 5",description:"Anthropic's most capable widely released model for demanding reasoning and long-horizon agentic work",match:{starts_with:"claude-fable-5"},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:10,cache_write_mtok:12.5,cache_read_mtok:1,output_mtok:50}},{id:"claude-haiku-4-5",name:"Claude Haiku 4.5",description:"Fastest and most intelligent Haiku model",match:{or:[{starts_with:"claude-haiku-4-5"},{starts_with:"claude-haiku-4.5"},{starts_with:"claude-4-5-haiku"},{starts_with:"claude-4.5-haiku"}]},context_window:2e5,prices:{input_mtok:1,cache_write_mtok:1.25,cache_read_mtok:.1,output_mtok:5}},{id:"claude-opus-4-0",name:"Claude Opus 4",description:"Most intelligent model for complex tasks",match:{or:[{starts_with:"claude-opus-4-0"},{starts_with:"claude-4-opus"},{equals:"claude-opus-4"},{equals:"claude-opus-4-20250514"}]},context_window:2e5,prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"claude-opus-4-1",name:"Claude Opus 4.1",description:"Most intelligent model for complex tasks",match:{or:[{starts_with:"claude-opus-4-1"},{starts_with:"claude-opus-4.1"}]},context_window:2e5,prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"claude-opus-4-5",name:"Claude Opus 4.5",description:"Premium model combining maximum intelligence with practical performance",match:{or:[{starts_with:"claude-opus-4-5"},{starts_with:"claude-opus-4.5"},{starts_with:"claude-4-5-opus"},{starts_with:"claude-4.5-opus"}]},context_window:2e5,prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"claude-opus-4-6",name:"Claude Opus 4.6",description:"Our most intelligent model for building agents and coding",match:{or:[{starts_with:"claude-opus-4-6"},{starts_with:"claude-opus-4.6"},{starts_with:"claude-4-6-opus"},{starts_with:"claude-4.6-opus"}]},context_window:2e5,prices:[{prices:{input_mtok:{base:5,tiers:[{start:2e5,price:10}]},cache_write_mtok:{base:6.25,tiers:[{start:2e5,price:12.5}]},cache_read_mtok:{base:.5,tiers:[{start:2e5,price:1}]},output_mtok:{base:25,tiers:[{start:2e5,price:37.5}]}}},{constraint:{start_date:"2026-03-13",type:"start_date"},prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}}]},{id:"claude-opus-4-7",name:"Claude Opus 4.7",description:"Our most capable model for complex reasoning and agentic coding",match:{or:[{starts_with:"claude-opus-4-7"},{starts_with:"claude-opus-4.7"},{starts_with:"claude-4-7-opus"},{starts_with:"claude-4.7-opus"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"claude-opus-4-8",name:"Claude Opus 4.8",description:"Our most capable model for complex reasoning and agentic coding",match:{or:[{starts_with:"claude-opus-4-8"},{starts_with:"claude-opus-4.8"},{starts_with:"claude-4-8-opus"},{starts_with:"claude-4.8-opus"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"claude-sonnet-4-0",name:"Claude Sonnet 4",description:"Optimal balance of intelligence, cost, and speed",match:{or:[{starts_with:"claude-sonnet-4-2025"},{starts_with:"claude-sonnet-4-0"},{starts_with:"claude-sonnet-4@"},{equals:"claude-sonnet-4"},{starts_with:"claude-4-sonnet"}]},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-sonnet-4-5",name:"Claude Sonnet 4.5",description:"Our best combination of speed and intelligence",match:{or:[{starts_with:"claude-sonnet-4-5"},{starts_with:"claude-sonnet-4.5"}]},context_window:1e6,prices:{input_mtok:{base:3,tiers:[{start:2e5,price:6}]},cache_write_mtok:{base:3.75,tiers:[{start:2e5,price:7.5}]},cache_read_mtok:{base:.3,tiers:[{start:2e5,price:.6}]},output_mtok:{base:15,tiers:[{start:2e5,price:22.5}]}}},{id:"claude-sonnet-4-6",name:"Claude Sonnet 4.6",description:"Our best combination of speed and intelligence",match:{or:[{starts_with:"claude-sonnet-4-6"},{starts_with:"claude-sonnet-4.6"}]},context_window:1e6,prices:[{prices:{input_mtok:{base:3,tiers:[{start:2e5,price:6}]},cache_write_mtok:{base:3.75,tiers:[{start:2e5,price:7.5}]},cache_read_mtok:{base:.3,tiers:[{start:2e5,price:.6}]},output_mtok:{base:15,tiers:[{start:2e5,price:22.5}]}}},{constraint:{start_date:"2026-03-13",type:"start_date"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}}]},{id:"claude-v1",description:"Retired, here to match price sources",match:{equals:"claude-v1"},prices:{input_mtok:8,output_mtok:24}}]},{id:"avian",name:"Avian",pricing_urls:["https://avian.io/pricing/"],api_pattern:"https://api\\.avian\\.io",models:[{id:"Meta-Llama-3.1-405B-Instruct",match:{equals:"Meta-Llama-3.1-405B-Instruct"},prices:{input_mtok:1.5,output_mtok:1.5}},{id:"Meta-Llama-3.1-70B-Instruct",match:{equals:"Meta-Llama-3.1-70B-Instruct"},prices:{input_mtok:.45,output_mtok:.45}},{id:"Meta-Llama-3.1-8B-Instruct",match:{equals:"Meta-Llama-3.1-8B-Instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"Meta-Llama-3.3-70B-Instruct",match:{equals:"Meta-Llama-3.3-70B-Instruct"},prices:{input_mtok:.45,output_mtok:.45}}]},{id:"aws",name:"AWS Bedrock",pricing_urls:["https://aws.amazon.com/bedrock/pricing/"],api_pattern:"https://bedrock-runtime\\.[a-z0-9-]+\\.amazonaws\\.com/",provider_match:{or:[{contains:"bedrock"},{contains:"amazon"}]},extractors:[{api_flavor:"default",root:"usage",model_path:"model",mappings:[{path:"inputTokens",dest:"input_tokens",required:!0},{path:"outputTokens",dest:"output_tokens",required:!0}]},{api_flavor:"anthropic",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:"cache_creation_input_tokens",dest:"input_tokens",required:!1},{path:"cache_read_input_tokens",dest:"input_tokens",required:!1},{path:"cache_creation_input_tokens",dest:"cache_write_tokens",required:!1},{path:"cache_read_input_tokens",dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"amazon.nova-lite-v1:0",name:"Nova Lite",description:"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy.",match:{contains:"amazon.nova-lite"},prices:{input_mtok:.06,cache_read_mtok:.015,output_mtok:.24}},{id:"amazon.nova-micro-v1:0",name:"Nova Micro",description:"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for speed and cost, Amazon Nova Micro excels at tasks such as text summarization, translation, content classification, interactive chat, and brainstorming. It has simple mathematical reasoning and coding abilities.",match:{contains:"amazon.nova-micro"},prices:{input_mtok:.035,cache_read_mtok:.00875,output_mtok:.14}},{id:"amazon.nova-premier-v1:0",name:"Nova Premier",match:{contains:"amazon.nova-premier"},prices:{input_mtok:2.5,cache_read_mtok:.625,output_mtok:12.5}},{id:"amazon.nova-pro-v1:0",name:"Nova Pro",description:"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on key benchmarks including visual question answering (TextVQA) and video understanding (VATEX).",match:{contains:"amazon.nova-pro"},prices:{input_mtok:.8,cache_read_mtok:.2,output_mtok:3.2}},{id:"amazon.nova-sonic-v1:0",name:"Nova Sonic",match:{contains:"amazon.nova-sonic"},prices:{input_mtok:.06,output_mtok:.24,input_audio_mtok:3.4,output_audio_mtok:13.6}},{id:"amazon.titan-embed-text-v1",name:"Titan Embeddings G1 - Text",match:{contains:"amazon.titan-embed-text"},prices:{input_mtok:.1}},{id:"amazon.titan-text-express-v1",name:"Titan Text G1 - Express",match:{contains:"titan-text-express"},prices:{input_mtok:.2,output_mtok:.6}},{id:"amazon.titan-text-lite-v1",name:"Titan Text G1 - Lite",match:{contains:"titan-text-lite"},prices:{input_mtok:.15,output_mtok:.2}},{id:"deepseek.r1-v1:0",name:"DeepSeek-R1",match:{contains:"deepseek.r1"},prices:{input_mtok:1.35,output_mtok:5.4}},{id:"global.anthropic.claude-fable-5-v1:0",match:{contains:"global.anthropic.claude-fable-5"},prices:{input_mtok:10,cache_write_mtok:12.5,cache_read_mtok:1,output_mtok:50}},{id:"global.anthropic.claude-haiku-4-5-20251001-v1:0",match:{contains:"global.anthropic.claude-haiku-4-5-20251001"},prices:{input_mtok:1,cache_write_mtok:1.25,cache_read_mtok:.1,output_mtok:5}},{id:"global.anthropic.claude-opus-4-5-v1:0",match:{contains:"global.anthropic.claude-opus-4-5"},prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"global.anthropic.claude-opus-4-6-v1:0",match:{contains:"global.anthropic.claude-opus-4-6"},prices:{input_mtok:{base:5,tiers:[{start:2e5,price:10}]},cache_write_mtok:{base:6.25,tiers:[{start:2e5,price:12.5}]},cache_read_mtok:{base:.5,tiers:[{start:2e5,price:1}]},output_mtok:{base:25,tiers:[{start:2e5,price:37.5}]}}},{id:"global.anthropic.claude-opus-4-7-v1:0",match:{contains:"global.anthropic.claude-opus-4-7"},prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"global.anthropic.claude-opus-4-8-v1:0",match:{contains:"global.anthropic.claude-opus-4-8"},prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"global.anthropic.claude-sonnet-4-20250514-v1:0",match:{contains:"global.anthropic.claude-sonnet-4-20250514"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"global.anthropic.claude-sonnet-4-5-20250929-v1:0",match:{contains:"global.anthropic.claude-sonnet-4-5-20250929"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"global.anthropic.claude-sonnet-4-6-v1:0",match:{contains:"global.anthropic.claude-sonnet-4-6"},prices:{input_mtok:{base:3,tiers:[{start:2e5,price:6}]},cache_write_mtok:{base:3.75,tiers:[{start:2e5,price:7.5}]},cache_read_mtok:{base:.3,tiers:[{start:2e5,price:.6}]},output_mtok:{base:15,tiers:[{start:2e5,price:22.5}]}}},{id:"google.gemma-3-12b-it",name:"Gemma 3 12B IT",match:{contains:"google.gemma-3-12b-it"},prices:{input_mtok:.09,output_mtok:.29}},{id:"google.gemma-3-27b-it",name:"Gemma 3 27B IT",match:{contains:"google.gemma-3-27b-it"},prices:{input_mtok:.23,output_mtok:.38}},{id:"google.gemma-3-4b-it",name:"Gemma 3 4B IT",match:{contains:"google.gemma-3-4b-it"},prices:{input_mtok:.04,output_mtok:.08}},{id:"meta.llama3-1-70b-instruct-v1:0",name:"Llama 3.1 70B Instruct",match:{contains:"meta.llama3-1-70b-instruct"},prices:{input_mtok:.72,output_mtok:.72}},{id:"meta.llama3-1-8b-instruct-v1:0",name:"Llama 3.1 8B Instruct",match:{contains:"meta.llama3-1-8b-instruct"},prices:{input_mtok:.22,output_mtok:.22}},{id:"meta.llama3-2-11b-instruct-v1:0",name:"Llama 3.2 11B Instruct",match:{contains:"meta.llama3-2-11b-instruct"},prices:{input_mtok:.16,output_mtok:.16}},{id:"meta.llama3-2-1b-instruct-v1:0",name:"Llama 3.2 1B Instruct",match:{contains:"meta.llama3-2-1b-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"meta.llama3-2-3b-instruct-v1:0",name:"Llama 3.2 3B Instruct",match:{contains:"meta.llama3-2-3b-instruct"},prices:{input_mtok:.15,output_mtok:.15}},{id:"meta.llama3-2-90b-instruct-v1:0",name:"Llama 3.2 90B Instruct",match:{contains:"meta.llama3-2-90b-instruct"},prices:{input_mtok:.72,output_mtok:.72}},{id:"meta.llama3-3-70b-instruct-v1:0",name:"Llama 3.3 70B Instruct",match:{contains:"meta.llama3-3-70b-instruct"},prices:{input_mtok:.72,output_mtok:.72}},{id:"meta.llama3-70b-instruct-v1:0",name:"Llama 3 70B Instruct",match:{contains:"meta.llama3-70b-instruct"},prices:{input_mtok:2.65,output_mtok:3.5}},{id:"meta.llama3-8b-instruct-v1:0",name:"Llama 3 8B Instruct",match:{contains:"meta.llama3-8b-instruct"},prices:{input_mtok:.3,output_mtok:.6}},{id:"meta.llama4-maverick-17b-instruct-v1:0",name:"Llama 4 Maverick 17B Instruct",match:{contains:"meta.llama4-maverick-17b-instruct"},prices:{input_mtok:.24,output_mtok:.97}},{id:"meta.llama4-scout-17b-instruct-v1:0",name:"Llama 4 Scout 17B Instruct",match:{contains:"meta.llama4-scout-17b-instruct"},prices:{input_mtok:.17,output_mtok:.66}},{id:"mistral.devstral-2-123b",name:"Devstral 2 123B",match:{contains:"mistral.devstral-2-123b"},prices:{input_mtok:.4,output_mtok:2}},{id:"mistral.magistral-small-2509",name:"Magistral Small 2509",match:{contains:"mistral.magistral-small-2509"},prices:{input_mtok:.5,output_mtok:1.5}},{id:"mistral.ministral-3-14b-instruct",name:"Ministral 14B 3.0",match:{contains:"mistral.ministral-3-14b-instruct"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistral.ministral-3-3b-instruct",name:"Ministral 3B 3.0",match:{contains:"mistral.ministral-3-3b-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistral.ministral-3-8b-instruct",name:"Ministral 8B 3.0",match:{contains:"mistral.ministral-3-8b-instruct"},prices:{input_mtok:.15,output_mtok:.15}},{id:"mistral.mistral-7b-instruct-v0:2",name:"Mistral 7B Instruct",match:{contains:"mistral.mistral-7b-instruct-v0"},prices:{input_mtok:.15,output_mtok:.2}},{id:"mistral.mistral-large-2402-v1:0",name:"Mistral Large (24.02)",match:{contains:"mistral.mistral-large-2402"},prices:{input_mtok:4,output_mtok:12}},{id:"mistral.mistral-large-3-675b-instruct",name:"Mistral Large 3",match:{contains:"mistral.mistral-large-3-675b-instruct"},prices:{input_mtok:.5,output_mtok:1.5}},{id:"mistral.mistral-small-2402-v1:0",name:"Mistral Small (24.02)",match:{contains:"mistral.mistral-small-2402"},prices:{input_mtok:1,output_mtok:3}},{id:"mistral.mixtral-8x7b-instruct-v0:1",name:"Mixtral 8x7B Instruct",match:{contains:"mistral.mixtral-8x7b-instruct-v0"},prices:{input_mtok:.45,output_mtok:.7}},{id:"mistral.pixtral-large-2502-v1:0",name:"Pixtral Large (25.02)",match:{contains:"mistral.pixtral-large-2502"},prices:{input_mtok:2,output_mtok:6}},{id:"mistral.voxtral-mini-3b-2507",name:"Voxtral Mini 3B 2507",match:{contains:"mistral.voxtral-mini-3b-2507"},prices:{input_mtok:.04,output_mtok:.04}},{id:"mistral.voxtral-small-24b-2507",name:"Voxtral Small 24B 2507",match:{contains:"mistral.voxtral-small-24b-2507"},prices:{input_mtok:.1,output_mtok:.3}},{id:"nvidia.nemotron-nano-3-30b:0",name:"Nemotron 3 Nano 30B",match:{contains:"nvidia.nemotron-nano-3-30b"},prices:{input_mtok:.06,output_mtok:.24}},{id:"nvidia.nemotron-nano-9b-v2:0",name:"Nemotron 2 Nano 9B",match:{contains:"nvidia.nemotron-nano-9b-v2"},prices:{input_mtok:.06,output_mtok:.23}},{id:"nvidia.nemotron-super-3-120b:0",name:"Nemotron 3 Super 120B",match:{contains:"nvidia.nemotron-super-3-120b"},prices:{input_mtok:.15,output_mtok:.65}},{id:"openai.gpt-oss-120b-1:0",name:"gpt-oss-120b",match:{contains:"openai.gpt-oss-120b-1"},prices:{input_mtok:.15,output_mtok:.6}},{id:"openai.gpt-oss-20b-1:0",name:"gpt-oss-20b",match:{contains:"openai.gpt-oss-20b-1"},prices:{input_mtok:.07,output_mtok:.3}},{id:"qwen.qwen3-32b-v1:0",name:"Qwen3 32B (dense)",match:{contains:"qwen.qwen3-32b"},prices:{input_mtok:.15,output_mtok:.6}},{id:"qwen.qwen3-coder-30b-a3b-v1:0",name:"Qwen3-Coder-30B-A3B-Instruct",match:{contains:"qwen.qwen3-coder-30b-a3b"},prices:{input_mtok:.15,output_mtok:.6}},{id:"qwen.qwen3-coder-480b-a35b-v1:0",name:"Qwen3-Coder-480B-A35B-Instruct",match:{contains:"qwen.qwen3-coder-480b-a35b"},prices:{input_mtok:.45,output_mtok:1.8}},{id:"qwen.qwen3-vl-235b-a22b-v1:0",name:"Qwen3-VL-235B-A22B-Instruct",match:{contains:"qwen.qwen3-vl-235b-a22b"},prices:{input_mtok:.53,output_mtok:2.66}},{id:"regional.anthropic.claude-3-5-haiku-20241022-v1:0",match:{contains:"claude-3-5-haiku-20241022"},prices:{input_mtok:.8,cache_write_mtok:1,cache_read_mtok:.08,output_mtok:4}},{id:"regional.anthropic.claude-3-5-sonnet-20240620-v1:0",match:{contains:"claude-3-5-sonnet-20240620"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"regional.anthropic.claude-3-5-sonnet-20241022-v2:0",match:{contains:"claude-3-5-sonnet-20241022"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"regional.anthropic.claude-3-7-sonnet-20250219-v1:0",match:{contains:"claude-3-7-sonnet-20250219"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"regional.anthropic.claude-3-haiku-20240307-v1:0",match:{contains:"claude-3-haiku-20240307"},prices:{input_mtok:.25,output_mtok:1.25}},{id:"regional.anthropic.claude-3-opus-20240229-v1:0",match:{contains:"claude-3-opus-20240229"},prices:{input_mtok:15,output_mtok:75}},{id:"regional.anthropic.claude-3-sonnet-20240229-v1:0",match:{contains:"claude-3-sonnet-20240229"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"regional.anthropic.claude-fable-5-v1:0",match:{or:[{starts_with:"anthropic.claude-fable-5"},{starts_with:"claude-fable-5"},{contains:"us.anthropic.claude-fable-5"},{contains:"au.anthropic.claude-fable-5"},{contains:"eu.anthropic.claude-fable-5"},{contains:"jp.anthropic.claude-fable-5"}]},prices:{input_mtok:11,cache_write_mtok:13.75,cache_read_mtok:1.1,output_mtok:55}},{id:"regional.anthropic.claude-haiku-4-5-20251001-v1:0",match:{or:[{starts_with:"anthropic.claude-haiku-4-5-20251001"},{starts_with:"claude-haiku-4-5-20251001"},{contains:"us.anthropic.claude-haiku-4-5-20251001"},{contains:"au.anthropic.claude-haiku-4-5-20251001"},{contains:"apac.anthropic.claude-haiku-4-5-20251001"},{contains:"eu.anthropic.claude-haiku-4-5-20251001"},{contains:"us-gov.anthropic.claude-haiku-4-5-20251001"},{contains:"jp.anthropic.claude-haiku-4-5-20251001"}]},prices:{input_mtok:1.1,cache_write_mtok:1.375,cache_read_mtok:.11,output_mtok:5.5}},{id:"regional.anthropic.claude-opus-4-1-20250805-v1:0",match:{or:[{starts_with:"anthropic.claude-opus-4-1-20250805"},{starts_with:"claude-opus-4-1-20250805"},{contains:"us.anthropic.claude-opus-4-1-20250805"},{contains:"au.anthropic.claude-opus-4-1-20250805"},{contains:"apac.anthropic.claude-opus-4-1-20250805"},{contains:"eu.anthropic.claude-opus-4-1-20250805"},{contains:"us-gov.anthropic.claude-opus-4-1-20250805"},{contains:"jp.anthropic.claude-opus-4-1-20250805"}]},prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"regional.anthropic.claude-opus-4-20250514-v1:0",match:{or:[{starts_with:"anthropic.claude-opus-4-20250514"},{starts_with:"claude-opus-4-20250514"},{contains:"us.anthropic.claude-opus-4-20250514"},{contains:"au.anthropic.claude-opus-4-20250514"},{contains:"apac.anthropic.claude-opus-4-20250514"},{contains:"eu.anthropic.claude-opus-4-20250514"},{contains:"us-gov.anthropic.claude-opus-4-20250514"},{contains:"jp.anthropic.claude-opus-4-20250514"}]},prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"regional.anthropic.claude-opus-4-5-v1:0",match:{or:[{starts_with:"anthropic.claude-opus-4-5"},{starts_with:"claude-opus-4-5"},{contains:"us.anthropic.claude-opus-4-5"},{contains:"au.anthropic.claude-opus-4-5"},{contains:"apac.anthropic.claude-opus-4-5"},{contains:"eu.anthropic.claude-opus-4-5"},{contains:"us-gov.anthropic.claude-opus-4-5"},{contains:"jp.anthropic.claude-opus-4-5"}]},prices:{input_mtok:5.5,cache_write_mtok:6.875,cache_read_mtok:.55,output_mtok:27.5}},{id:"regional.anthropic.claude-opus-4-6-v1:0",match:{or:[{starts_with:"anthropic.claude-opus-4-6"},{starts_with:"claude-opus-4-6"},{contains:"us.anthropic.claude-opus-4-6"},{contains:"au.anthropic.claude-opus-4-6"},{contains:"apac.anthropic.claude-opus-4-6"},{contains:"eu.anthropic.claude-opus-4-6"},{contains:"us-gov.anthropic.claude-opus-4-6"},{contains:"jp.anthropic.claude-opus-4-6"}]},prices:{input_mtok:{base:5.5,tiers:[{start:2e5,price:11}]},cache_write_mtok:{base:6.875,tiers:[{start:2e5,price:13.75}]},cache_read_mtok:{base:.55,tiers:[{start:2e5,price:1.1}]},output_mtok:{base:27.5,tiers:[{start:2e5,price:41.25}]}}},{id:"regional.anthropic.claude-opus-4-7-v1:0",match:{or:[{starts_with:"anthropic.claude-opus-4-7"},{starts_with:"claude-opus-4-7"},{contains:"us.anthropic.claude-opus-4-7"},{contains:"au.anthropic.claude-opus-4-7"},{contains:"apac.anthropic.claude-opus-4-7"},{contains:"eu.anthropic.claude-opus-4-7"},{contains:"us-gov.anthropic.claude-opus-4-7"},{contains:"jp.anthropic.claude-opus-4-7"}]},prices:{input_mtok:5.5,cache_write_mtok:6.875,cache_read_mtok:.55,output_mtok:27.5}},{id:"regional.anthropic.claude-opus-4-8-v1:0",match:{or:[{starts_with:"anthropic.claude-opus-4-8"},{starts_with:"claude-opus-4-8"},{contains:"us.anthropic.claude-opus-4-8"},{contains:"au.anthropic.claude-opus-4-8"},{contains:"eu.anthropic.claude-opus-4-8"},{contains:"jp.anthropic.claude-opus-4-8"}]},prices:{input_mtok:5.5,cache_write_mtok:6.875,cache_read_mtok:.55,output_mtok:27.5}},{id:"regional.anthropic.claude-sonnet-4-20250514-v1:0",match:{or:[{starts_with:"anthropic.claude-sonnet-4-20250514"},{starts_with:"claude-sonnet-4-20250514"},{contains:"us.anthropic.claude-sonnet-4-20250514"},{contains:"au.anthropic.claude-sonnet-4-20250514"},{contains:"apac.anthropic.claude-sonnet-4-20250514"},{contains:"eu.anthropic.claude-sonnet-4-20250514"},{contains:"us-gov.anthropic.claude-sonnet-4-20250514"},{contains:"jp.anthropic.claude-sonnet-4-20250514"}]},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"regional.anthropic.claude-sonnet-4-5-20250929-v1:0",match:{or:[{starts_with:"anthropic.claude-sonnet-4-5-20250929"},{starts_with:"claude-sonnet-4-5-20250929"},{contains:"us.anthropic.claude-sonnet-4-5-20250929"},{contains:"au.anthropic.claude-sonnet-4-5-20250929"},{contains:"apac.anthropic.claude-sonnet-4-5-20250929"},{contains:"eu.anthropic.claude-sonnet-4-5-20250929"},{contains:"us-gov.anthropic.claude-sonnet-4-5-20250929"},{contains:"jp.anthropic.claude-sonnet-4-5-20250929"}]},prices:{input_mtok:3.3,cache_write_mtok:4.125,cache_read_mtok:.33,output_mtok:16.5}},{id:"regional.anthropic.claude-sonnet-4-6-v1:0",match:{or:[{starts_with:"anthropic.claude-sonnet-4-6"},{starts_with:"claude-sonnet-4-6"},{contains:"us.anthropic.claude-sonnet-4-6"},{contains:"au.anthropic.claude-sonnet-4-6"},{contains:"apac.anthropic.claude-sonnet-4-6"},{contains:"eu.anthropic.claude-sonnet-4-6"},{contains:"us-gov.anthropic.claude-sonnet-4-6"},{contains:"jp.anthropic.claude-sonnet-4-6"}]},prices:{input_mtok:{base:3.3,tiers:[{start:2e5,price:6.6}]},cache_write_mtok:{base:4.125,tiers:[{start:2e5,price:8.25}]},cache_read_mtok:{base:.33,tiers:[{start:2e5,price:.66}]},output_mtok:{base:16.5,tiers:[{start:2e5,price:24.75}]}}}]},{id:"azure",name:"Microsoft Azure",pricing_urls:["https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/#pricing"],api_pattern:"(https?://)?([^.]*\\.)?(?:openai\\.azure\\.com|azure-api\\.net|cognitiveservices\\.azure\\.com)",price_comments:'These are prices for "*-Global" models, prices for "Regional" models are often slightly higher. Retired models are listed at https://learn.microsoft.com/th-th/azure/ai-foundry/openai/concepts/legacy-models',extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"responses",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:["input_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"embeddings",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0}]},{api_flavor:"anthropic",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:"cache_creation_input_tokens",dest:"input_tokens",required:!1},{path:"cache_read_input_tokens",dest:"input_tokens",required:!1},{path:"cache_creation_input_tokens",dest:"cache_write_tokens",required:!1},{path:"cache_read_input_tokens",dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]}],fallback_model_providers:["openai","anthropic"],models:[{id:"ada",match:{or:[{equals:"ada"},{equals:"text-embedding-ada"},{equals:"text-embedding-ada-002"},{equals:"text-embedding-ada-002-v2"}]},prices:{input_mtok:.1}},{id:"babbage",match:{or:[{equals:"babbage"},{equals:"babbage-002"}]},prices:{input_mtok:.4}},{id:"curie",match:{or:[{equals:"curie"},{equals:"text-curie"},{equals:"text-curie-001"}]},prices:{input_mtok:2}},{id:"davinci",match:{or:[{equals:"davinci"},{equals:"davinci-002"},{equals:"text-davinci"},{equals:"text-davinci-002"}]},prices:{input_mtok:2}},{id:"mai-ds-r1:free",name:"MAI DS R1 (free)",description:"MAI-DS-R1 is a post-trained variant of DeepSeek-R1 developed by the Microsoft AI team to improve the model's responsiveness on previously blocked topics while enhancing its safety profile. Built on top of DeepSeek-R1's reasoning foundation, it integrates 110k examples from the Tulu-3 SFT dataset and 350k internally curated multilingual safety-alignment samples. The model retains strong reasoning, coding, and problem-solving capabilities, while unblocking a wide range of prompts previously restricted in R1.",match:{equals:"mai-ds-r1:free"},prices:{}},{id:"o1",match:{or:[{equals:"o1"},{equals:"o1-2024-12-17"},{equals:"o1-preview"},{equals:"o1-preview-2024-09-12"}]},prices:{input_mtok:15,cache_read_mtok:7.5,output_mtok:60}},{id:"o1-mini",match:{or:[{equals:"o1-mini"},{equals:"o1-mini-2024-09-12"}]},prices:{input_mtok:1.1,cache_read_mtok:.55,output_mtok:4.4}},{id:"o3-2025-04-16",match:{or:[{equals:"o3"},{equals:"o3-2025-04-16"}]},prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}},{id:"o3-mini",match:{or:[{equals:"o3-mini"},{equals:"o3-mini-2025-01-31"}]},prices:{input_mtok:1.1,cache_read_mtok:.55,output_mtok:4.4}},{id:"o4-mini",match:{or:[{contains:"o4-mini"},{contains:"o4-mini-2025-04-16"}]},prices:{input_mtok:1.1,cache_read_mtok:.28,output_mtok:4.4}},{id:"phi-3-medium-128k-instruct",name:"Phi-3 Medium 128K Instruct",description:"Phi-3 128K Medium is a powerful 14-billion parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference adjustments, it excels in tasks involving common sense, mathematics, logical reasoning, and code processing.",match:{equals:"phi-3-medium-128k-instruct"},prices:{input_mtok:1,output_mtok:1}},{id:"phi-3-mini-128k-instruct",name:"Phi-3 Mini 128K Instruct",description:"Phi-3 Mini is a powerful 3.8B parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference adjustments, it excels in tasks involving common sense, mathematics, logical reasoning, and code processing.",match:{equals:"phi-3-mini-128k-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"phi-3.5-mini-128k-instruct",name:"Phi-3.5 Mini 128K Instruct",description:"Phi-3.5 models are lightweight, state-of-the-art open models. These models were trained with Phi-3 datasets that include both synthetic data and the filtered, publicly available websites data, with a focus on high quality and reasoning-dense properties. Phi-3.5 Mini uses 3.8B parameters, and is a dense decoder-only transformer model using the same tokenizer as Phi-3 Mini.",match:{equals:"phi-3.5-mini-128k-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"phi-4",name:"Phi 4",description:"Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed.",match:{equals:"phi-4"},prices:{input_mtok:.07,output_mtok:.14}},{id:"phi-4-multimodal-instruct",name:"Phi 4 Multimodal Instruct",description:"Phi-4 Multimodal Instruct is a versatile 5.6B parameter foundation model that combines advanced reasoning and instruction-following capabilities across both text and visual inputs, providing accurate text outputs. The unified architecture enables efficient, low-latency inference, suitable for edge and mobile deployments. Phi-4 Multimodal Instruct supports text inputs in multiple languages including Arabic, Chinese, English, French, German, Japanese, Spanish, and more, with visual input optimized primarily for English. It delivers impressive performance on multimodal tasks involving mathematical, scientific, and document reasoning, providing developers and enterprises a powerful yet compact model for sophisticated interactive applications. For more information, see the Phi-4 Multimodal blog post.",match:{equals:"phi-4-multimodal-instruct"},prices:{input_mtok:.05,output_mtok:.1}},{id:"phi-4-reasoning-plus",name:"Phi 4 Reasoning Plus",description:"Phi-4-reasoning-plus is an enhanced 14B parameter model from Microsoft, fine-tuned from Phi-4 with additional reinforcement learning to boost accuracy on math, science, and code reasoning tasks. It uses the same dense decoder-only transformer architecture as Phi-4, but generates longer, more comprehensive outputs structured into a step-by-step reasoning trace and final answer.",match:{equals:"phi-4-reasoning-plus"},prices:{input_mtok:.07,output_mtok:.35}},{id:"phi-4-reasoning-plus:free",name:"Phi 4 Reasoning Plus (free)",description:"Phi-4-reasoning-plus is an enhanced 14B parameter model from Microsoft, fine-tuned from Phi-4 with additional reinforcement learning to boost accuracy on math, science, and code reasoning tasks. It uses the same dense decoder-only transformer architecture as Phi-4, but generates longer, more comprehensive outputs structured into a step-by-step reasoning trace and final answer.",match:{equals:"phi-4-reasoning-plus:free"},prices:{}},{id:"phi-4-reasoning:free",name:"Phi 4 Reasoning (free)",description:"Phi-4-reasoning is a 14B parameter dense decoder-only transformer developed by Microsoft, fine-tuned from Phi-4 to enhance complex reasoning capabilities. It uses a combination of supervised fine-tuning on chain-of-thought traces and reinforcement learning, targeting math, science, and code reasoning tasks. With a 32k context window and high inference efficiency, it is optimized for structured responses in a two-part format: reasoning trace followed by a final solution.",match:{equals:"phi-4-reasoning:free"},prices:{}},{id:"text-embedding-3-large",match:{equals:"text-embedding-3-large"},prices:{input_mtok:.13}},{id:"text-embedding-3-small",match:{equals:"text-embedding-3-small"},prices:{input_mtok:.02}},{id:"wizardlm-2-8x22b",name:"WizardLM-2 8x22B",description:"WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models.",match:{equals:"wizardlm-2-8x22b"},prices:{input_mtok:.48,output_mtok:.48}}]},{id:"cerebras",name:"Cerebras",pricing_urls:["https://www.cerebras.ai/pricing#pricing","https://inference-docs.cerebras.ai/models/openai-oss"],api_pattern:"https://api\\.cerebras\\.ai",model_match:{contains:"cerebras"},provider_match:{contains:"cerebras"},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"gpt-oss-120b",name:"GPT-OSS 120B",description:"OpenAI's flagship open source model, built on a Mixture-of-Experts (MoE) architecture with 120 billion parameters and 128 experts. Delivers frontier reasoning capabilities with record-breaking inference speeds on Cerebras hardware (~3,000 tokens/second).",match:{or:[{equals:"gpt-oss-120b"},{starts_with:"cerebras/gpt-oss-120b"},{starts_with:"cerebras:gpt-oss-120b"}]},context_window:131072,price_comments:"Developer tier pricing. Free tier: 65k context, Paid tier: 131k context.",prices:{input_mtok:.35,output_mtok:.75}},{id:"llama-3.3-70b",name:"Llama 3.3 70B",description:"Meta's enhanced 70B model delivering 405B-level accuracy. Optimized for chat, coding, instruction following, mathematics, and reasoning with high-speed inference on Cerebras hardware (~2,100 tokens/second).",match:{or:[{equals:"llama-3.3-70b"},{starts_with:"cerebras/llama-3.3-70b"},{starts_with:"cerebras:llama-3.3-70b"}]},context_window:128e3,price_comments:"Developer tier pricing. Free tier: 65k context, Paid tier: 128k context.",prices:{input_mtok:.85,output_mtok:1.2}},{id:"llama3.1-8b",name:"Llama 3.1 8B",description:"Meta's Llama 3.1 8B model for general-purpose tasks including chat, coding, and instruction following. Optimized for fast inference on Cerebras hardware (~2,200 tokens/second).",match:{or:[{equals:"llama3.1-8b"},{starts_with:"cerebras/llama3.1-8b"},{starts_with:"cerebras:llama3.1-8b"}]},context_window:32768,price_comments:"Developer tier pricing. Free tier: 8k context, Paid tier: 32k context.",prices:{input_mtok:.1,output_mtok:.1}},{id:"qwen-3-32b",name:"Qwen 3 32B",description:"Qwen's 32B parameter model with enhanced reasoning and coding capabilities. Supports both standard and reasoning modes for complex tasks, with fast inference speeds on Cerebras hardware (~2,600 tokens/second).",match:{or:[{equals:"qwen-3-32b"},{starts_with:"cerebras/qwen-3-32b"},{starts_with:"cerebras:qwen-3-32b"}]},context_window:131072,price_comments:"Developer tier pricing. Free tier: 65k context, Paid tier: 131k context.",prices:{input_mtok:.4,output_mtok:.8}},{id:"qwen-3-coder-480b",name:"qwen-3-coder-480b",match:{equals:"qwen-3-coder-480b"},price_comments:"Seems to be no longer available on cerebras, here to help with tests",prices:{}}]},{id:"cohere",name:"Cohere",pricing_urls:["https://cohere.com/pricing"],api_pattern:"https://api\\.cohere\\.ai",model_match:{starts_with:"command-"},provider_match:{contains:"cohere"},extractors:[{api_flavor:"default",root:["usage","billed_units"],model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:"output_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"embeddings",root:["meta","billed_units"],model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0}]}],models:[{id:"command",name:"Command",description:"Command is an instruction-following conversational model that performs language tasks with high quality, more reliably and with a longer context than our base generative models.",match:{equals:"command"},prices:{input_mtok:1,output_mtok:2}},{id:"command-a",name:"Command A",description:`Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases.
3
- Compared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.`,match:{starts_with:"command-a"},prices:{input_mtok:2.5,output_mtok:10}},{id:"command-r",name:"Command R",description:"Command-R is a 35B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents.",match:{or:[{equals:"command-r"},{equals:"command-r-08-2024"}]},prices:{input_mtok:.15,output_mtok:.6}},{id:"command-r-plus",name:"Command R+",description:"Command R+ is a new, 104B-parameter LLM from Cohere. It's useful for roleplay, general consumer usecases, and Retrieval Augmented Generation (RAG).",match:{or:[{equals:"command-r-plus"},{equals:"command-r-plus-08-2024"}]},prices:{input_mtok:2.5,output_mtok:10}},{id:"command-r7b",name:"Command R7B",description:"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps.",match:{or:[{equals:"command-r7b"},{equals:"command-r7b-12-2024"}]},prices:{input_mtok:.0375,output_mtok:.15}},{id:"embed-v4.0",name:"Embed v4.0",description:"Embed v4.0 is a state-of-the-art embedding model designed for precise retrieval across noisy, multilingual, and multimodal data.",match:{equals:"embed-v4.0"},context_window:128e3,prices:{input_mtok:.12}}]},{id:"deepseek",name:"Deepseek",pricing_urls:["https://api-docs.deepseek.com/quick_start/pricing"],api_pattern:"https://api\\.deepseek\\.com",price_comments:'Deepseek off-peak pricing applies "UTC 16:30-00:30" so we switch it around and use the off-peak pricing as the default (first) price then the second price with a constraint is the "standard" pricing that applies "UTC 00:30-16:30".',model_match:{contains:"deepseek"},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"deepseek-chat",name:"DeepSeek Chat",description:"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.",match:{or:[{starts_with:"deepseek-chat"},{equals:"deepseek-chat-v3-0324"}]},context_window:64e3,prices:[{prices:{input_mtok:.135,cache_read_mtok:.035,output_mtok:.55}},{constraint:{start_time:"00:30:00Z",end_time:"16:30:00Z",type:"time_of_date"},prices:{input_mtok:.27,cache_read_mtok:.07,output_mtok:1.1}}]},{id:"deepseek-reasoner",name:"Deepseek R1",description:"DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.",match:{or:[{equals:"deepseek-reasoner"},{starts_with:"deepseek-r1"},{equals:"deepseek-r1-0528"}]},context_window:64e3,prices:[{prices:{input_mtok:.135,cache_read_mtok:.035,output_mtok:.55}},{constraint:{start_time:"00:30:00Z",end_time:"16:30:00Z",type:"time_of_date"},prices:{input_mtok:.55,cache_read_mtok:.14,output_mtok:2.19}}]},{id:"deepseek-v4-flash",name:"DeepSeek V4 Flash",description:"DeepSeek-V4-Flash. Supports both non-thinking and thinking (default) modes, JSON output, tool calls, chat prefix completion, and FIM completion (non-thinking only).",match:{or:[{starts_with:"deepseek-v4-flash"}]},context_window:1e6,prices:{input_mtok:.14,cache_read_mtok:.0028,output_mtok:.28}},{id:"deepseek-v4-pro",name:"DeepSeek V4 Pro",description:"DeepSeek-V4-Pro. Supports both non-thinking and thinking (default) modes, JSON output, tool calls, chat prefix completion, and FIM completion (non-thinking only).",match:{or:[{starts_with:"deepseek-v4-pro"}]},context_window:1e6,prices:{input_mtok:.435,cache_read_mtok:.003625,output_mtok:.87}}]},{id:"doubleword",name:"Doubleword",pricing_urls:["https://docs.doubleword.ai/inference-api/models"],api_pattern:"https://api\\.doubleword\\.ai",price_comments:"Doubleword publishes Realtime, Async, and Batch prices. This provider currently encodes only Realtime pricing.",extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","cache_write_tokens"],dest:"cache_write_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"responses",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:["input_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"embeddings",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0}]}],models:[{id:"Qwen/Qwen3-14B-FP8",name:"Qwen3 14B",match:{equals:"Qwen/Qwen3-14B-FP8"},prices:{input_mtok:.05,output_mtok:.6}},{id:"Qwen/Qwen3-Embedding-8B",name:"Qwen3 Embedding 8B",match:{equals:"Qwen/Qwen3-Embedding-8B"},prices:{input_mtok:.04}},{id:"Qwen/Qwen3-VL-235B-A22B-Instruct-FP8",name:"Qwen3 VL 235B A22B Instruct",match:{equals:"Qwen/Qwen3-VL-235B-A22B-Instruct-FP8"},prices:{input_mtok:.6,output_mtok:1.2}},{id:"Qwen/Qwen3-VL-30B-A3B-Instruct-FP8",name:"Qwen3 VL 30B A3B Instruct",match:{equals:"Qwen/Qwen3-VL-30B-A3B-Instruct-FP8"},prices:{input_mtok:.16,output_mtok:.8}},{id:"Qwen/Qwen3.5-35B-A3B-FP8",name:"Qwen3.5 35B A3B",match:{equals:"Qwen/Qwen3.5-35B-A3B-FP8"},prices:{input_mtok:.25,output_mtok:2}},{id:"Qwen/Qwen3.5-397B-A17B",name:"Qwen3.5 397B A17B",match:{equals:"Qwen/Qwen3.5-397B-A17B"},prices:{input_mtok:.6,output_mtok:3.6}},{id:"Qwen/Qwen3.5-9B",name:"Qwen3.5 9B",match:{equals:"Qwen/Qwen3.5-9B"},prices:{input_mtok:.08,output_mtok:.7}},{id:"Qwen/Qwen3.6-35B-A3B-FP8",name:"Qwen3.6 35B A3B",match:{equals:"Qwen/Qwen3.6-35B-A3B-FP8"},prices:{input_mtok:.25,output_mtok:2}},{id:"deepseek-ai/DeepSeek-V4-Flash",name:"DeepSeek V4 Flash",match:{equals:"deepseek-ai/DeepSeek-V4-Flash"},prices:{input_mtok:.14,output_mtok:.28}},{id:"deepseek-ai/DeepSeek-V4-Pro",name:"DeepSeek V4 Pro",match:{equals:"deepseek-ai/DeepSeek-V4-Pro"},prices:{input_mtok:1.74,output_mtok:3.48}},{id:"google/gemma-4-31B-it",name:"Gemma 4 31B IT",match:{equals:"google/gemma-4-31B-it"},prices:{input_mtok:.14,output_mtok:.4}},{id:"mistralai/Devstral-2-123B-Instruct-2512",name:"Devstral 2 123B Instruct 2512",match:{equals:"mistralai/Devstral-2-123B-Instruct-2512"},prices:{input_mtok:.4,output_mtok:2}},{id:"moonshotai/Kimi-K2.6",name:"Kimi K2.6",match:{equals:"moonshotai/Kimi-K2.6"},prices:{input_mtok:.95,output_mtok:4}},{id:"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4",name:"Nemotron 3 Super 120B A12B",match:{equals:"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4"},prices:{input_mtok:.3,output_mtok:.75}},{id:"openai/gpt-oss-20b",name:"GPT OSS 20B",match:{equals:"openai/gpt-oss-20b"},prices:{input_mtok:.04,output_mtok:.3}},{id:"zai-org/GLM-5.1-FP8",name:"GLM 5.1",match:{equals:"zai-org/GLM-5.1-FP8"},prices:{input_mtok:1.4,output_mtok:4.4}}]},{id:"fireworks",name:"Fireworks",pricing_urls:["https://fireworks.ai/pricing"],api_pattern:"https://api\\.fireworks\\.ai",model_match:{starts_with:"accounts/fireworks/models/"},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"deepseek-r1-0528",name:"DeepSeek R1 0528",description:"The updated DeepSeek-R1-0528 model delivers major improvements in reasoning, inference, and accuracy through enhanced post-training optimization and greater computational resources. It now performs at a level approaching top-tier models like O3 and Gemini 2.5 Pro, with notable gains in complex tasks such as math and programming.",match:{equals:"accounts/fireworks/models/deepseek-r1-0528"},context_window:16e4,prices:{input_mtok:3,output_mtok:8}},{id:"deepseek-v3-0324",name:"Deepseek V3 03-24",description:"A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token from Deepseek. Updated checkpoint.",match:{equals:"accounts/fireworks/models/deepseek-v3-0324"},context_window:16e4,price_comments:`docs give just one price - "Pricing Per 1M Tokens", we assume that's input and output`,prices:{input_mtok:.9,output_mtok:.9}},{id:"deepseek-v3p2",name:"Deepseek V3.2",description:"Model from Deepseek that harmonizes high computational efficiency with superior reasoning and agent performance. 675B parameter MoE model.",match:{equals:"accounts/fireworks/models/deepseek-v3p2"},context_window:163840,prices:{input_mtok:.56,cache_read_mtok:.28,output_mtok:1.68}},{id:"gemma-3-27b-it",name:"Gemma 3 27B Instruct",match:{equals:"accounts/fireworks/models/gemma-3-27b-it"},context_window:131e3,price_comments:`docs give just one price - "Pricing Per 1M Tokens", we assume that's input and output`,prices:{input_mtok:.1,output_mtok:.1}},{id:"glm-4p7",name:"GLM-4.7",description:"Next-generation general-purpose model from Z.ai optimized for coding, reasoning, and agentic workflows. 352B parameter MoE model with advanced thinking controls.",match:{equals:"accounts/fireworks/models/glm-4p7"},context_window:202752,prices:{input_mtok:.6,output_mtok:2.2}},{id:"gpt-oss-120b",name:"OpenAI gpt-oss-120b",description:"OpenAI's open-weight 117B parameter MoE model designed for production, general purpose, high reasoning use-cases. Features powerful reasoning, agentic tasks, and versatile developer use cases.",match:{equals:"accounts/fireworks/models/gpt-oss-120b"},context_window:131072,prices:{input_mtok:.15,cache_read_mtok:.07,output_mtok:.6}},{id:"gpt-oss-20b",name:"OpenAI gpt-oss-20b",description:"OpenAI's open-weight 21.5B parameter model designed for powerful reasoning, agentic tasks, and versatile developer use cases. Optimized for lower latency and local or specialized tasks.",match:{equals:"accounts/fireworks/models/gpt-oss-20b"},context_window:131072,prices:{input_mtok:.07,cache_read_mtok:.04,output_mtok:.3}},{id:"kimi-k2p5",name:"Kimi K2.5",description:"Moonshot AI's flagship agentic model. Unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model. 1T parameter MoE model.",match:{equals:"accounts/fireworks/models/kimi-k2p5"},context_window:262144,prices:{input_mtok:.6,cache_read_mtok:.1,output_mtok:3}},{id:"llama-v3p1-8b-instruct",name:"Llama 3.1 8B Instruct",description:"The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes. The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.",match:{equals:"accounts/fireworks/models/llama-v3p1-8b-instruct"},context_window:131e3,price_comments:`docs give just one price - "Pricing Per 1M Tokens", we assume that's input and output`,prices:{input_mtok:.2,output_mtok:.2}},{id:"llama4-maverick-instruct-basic",name:"Llama 4 Maverick Instruct (Basic)",description:"The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes. The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.",match:{equals:"accounts/fireworks/models/llama4-maverick-instruct-basic"},context_window:1e6,prices:{input_mtok:.22,output_mtok:.88}},{id:"minimax-m2p1",name:"MiniMax-M2.1",description:"Built for strong real-world performance across complex, multi-language, and agent-driven workflows. 228B parameter model with robust support for systems, backend, web, mobile, and office-style tasks.",match:{equals:"accounts/fireworks/models/minimax-m2p1"},context_window:204800,prices:{input_mtok:.3,output_mtok:1.2}},{id:"qwen2p5-vl-72b-instruct",name:"Qwen2.5-VL 72B Instruct",description:"Latest Qwen's VLM model",match:{equals:"accounts/fireworks/models/qwen2p5-vl-72b-instruct"},context_window:128e3,price_comments:`docs give just one price - "Pricing Per 1M Tokens", we assume that's input and output`,prices:{input_mtok:.9,output_mtok:.9}},{id:"qwen3-235b-a22b",name:"Qwen3 235B-A22B",description:'Qwen3 is the latest evolution in the Qwen LLM series, featuring both dense and MoE models with major advancements in reasoning, agent capabilities, multilingual support, and instruction following. It uniquely allows seamless switching between "thinking" (for complex logic, math, coding) and "non-thinking" modes (for fast, general dialogue), delivering strong performance across tasks.',match:{equals:"accounts/fireworks/models/qwen3-235b-a22b"},context_window:128e3,prices:{input_mtok:.22,output_mtok:.88}}]},{id:"google",name:"Google",pricing_urls:["https://ai.google.dev/gemini-api/docs/pricing","https://cloud.google.com/vertex-ai/generative-ai/pricing"],api_pattern:"https://(.*\\.)?googleapis\\.com",model_match:{contains:"gemini"},provider_match:{or:[{contains:"google"},{contains:"vertex"},{contains:"gemini"}]},extractors:[{api_flavor:"default",root:"usageMetadata",model_path:"modelVersion",mappings:[{path:"promptTokenCount",dest:"input_tokens",required:!1},{path:"cachedContentTokenCount",dest:"cache_read_tokens",required:!1},{path:["cacheTokensDetails",{type:"array-match",field:"modality",match:{equals:"AUDIO"}},"tokenCount"],dest:"cache_audio_read_tokens",required:!1},{path:["promptTokensDetails",{type:"array-match",field:"modality",match:{equals:"AUDIO"}},"tokenCount"],dest:"input_audio_tokens",required:!1},{path:["candidatesTokensDetails",{type:"array-match",field:"modality",match:{equals:"AUDIO"}},"tokenCount"],dest:"output_audio_tokens",required:!1},{path:"candidatesTokenCount",dest:"output_tokens",required:!1},{path:"thoughtsTokenCount",dest:"output_tokens",required:!1},{path:"toolUsePromptTokenCount",dest:"input_tokens",required:!1}]},{api_flavor:"anthropic",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:"cache_creation_input_tokens",dest:"input_tokens",required:!1},{path:"cache_read_input_tokens",dest:"input_tokens",required:!1},{path:"cache_creation_input_tokens",dest:"cache_write_tokens",required:!1},{path:"cache_read_input_tokens",dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],fallback_model_providers:["anthropic"],models:[{id:"claude-3-5-haiku",match:{contains:"claude-3-5-haiku"},context_window:2e5,prices:{input_mtok:.8,cache_write_mtok:1,cache_read_mtok:.08,output_mtok:4}},{id:"claude-3-5-sonnet",match:{contains:"claude-3-5-sonnet"},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-3-7-sonnet",match:{contains:"claude-3-7-sonnet"},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-3-haiku",match:{contains:"claude-3-haiku"},context_window:2e5,prices:{input_mtok:.25,cache_write_mtok:.3,cache_read_mtok:.03,output_mtok:1.25}},{id:"claude-3-opus",match:{contains:"claude-3-opus"},prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"claude-4-opus",match:{or:[{contains:"claude-4-opus"},{contains:"claude-opus-4@"},{contains:"claude-opus-4-0"},{contains:"claude-opus-4-1"},{equals:"claude-opus-4"}]},context_window:2e5,prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"claude-4-sonnet",match:{or:[{contains:"claude-4-sonnet"},{contains:"claude-sonnet-4"}]},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-fable-5",match:{contains:"claude-fable-5"},context_window:1e6,price_comments:"Flat pricing across full 1M context window. Ref: https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models",prices:{input_mtok:10,cache_write_mtok:12.5,cache_read_mtok:1,output_mtok:50}},{id:"claude-opus-4-6",match:{or:[{contains:"claude-4-6-opus"},{contains:"claude-opus-4-6"},{contains:"claude-4.6-opus"},{contains:"claude-opus-4.6"}]},context_window:2e5,prices:{input_mtok:{base:5,tiers:[{start:2e5,price:10}]},cache_write_mtok:{base:6.25,tiers:[{start:2e5,price:12.5}]},cache_read_mtok:{base:.5,tiers:[{start:2e5,price:1}]},output_mtok:{base:25,tiers:[{start:2e5,price:37.5}]}}},{id:"claude-opus-4-7",match:{or:[{contains:"claude-4-7-opus"},{contains:"claude-opus-4-7"},{contains:"claude-4.7-opus"},{contains:"claude-opus-4.7"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window. Ref: https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"claude-opus-4-8",match:{or:[{contains:"claude-4-8-opus"},{contains:"claude-opus-4-8"},{contains:"claude-4.8-opus"},{contains:"claude-opus-4.8"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window. Ref: https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"gemini-1.0-pro-vision-001",name:"gemini 1.0 pro vision",description:"Google's first-generation advanced multimodal model that can understand text, code, and images. It provides strong reasoning capabilities and follows instructions effectively.",match:{equals:"gemini-1.0-pro-vision-001"},context_window:32768,price_comments:"I can't find anything about this model or it's pricing, so trusting the original source",prices:{input_mtok:.125,output_mtok:.375}},{id:"gemini-1.5-flash",name:"gemini 1.5 flash",description:"A faster, more cost-effective variant of Gemini 1.5 that maintains strong capabilities while optimizing for performance and cost efficiency. Suitable for production deployments requiring high throughput.",match:{contains:"gemini-1.5-flash"},context_window:1e6,prices:{input_mtok:{base:.075,tiers:[{start:128e3,price:.15}]},cache_read_mtok:{base:.01875,tiers:[{start:128e3,price:.0375}]},output_mtok:{base:.3,tiers:[{start:128e3,price:.6}]}}},{id:"gemini-1.5-pro",name:"gemini 1.5 Pro",description:"Google's most capable multimodal model with an extremely long context window of up to 1 million tokens. It excels at complex reasoning, long-form content processing, and multimodal understanding.",match:{contains:"gemini-1.5-pro"},context_window:1e6,prices:{input_mtok:{base:1.25,tiers:[{start:128e3,price:2.5}]},output_mtok:{base:5,tiers:[{start:128e3,price:10}]}}},{id:"gemini-2.0-flash",name:"gemini 2.0 flash",description:"The newest generation of Google's Gemini models, featuring improved reasoning, instruction following, and factual accuracy, with the Flash variant optimized for cost-efficiency and performance.",match:{or:[{ends_with:"gemini-2.0-flash"},{contains:"gemini-2.0-flash-0"},{contains:"gemini-2.0-flash-exp"},{contains:"gemini-2.0-flash-thinking"},{contains:"gemini-2.0-flash-latest"}]},context_window:1e6,prices:{input_mtok:.1,cache_read_mtok:.025,output_mtok:.4,input_audio_mtok:.7,cache_audio_read_mtok:.175}},{id:"gemini-2.0-flash-lite",name:"gemini 2.0 flash lite",description:"A lighter, more cost-effective version of Gemini 2.0 Flash, designed for applications requiring high efficiency while maintaining good performance. Ideal for high-volume, cost-sensitive deployments.",match:{contains:"gemini-2.0-flash-lite"},context_window:1e6,prices:{input_mtok:.075,output_mtok:.3}},{id:"gemini-2.5-flash",name:"Gemini 2.5 Flash",description:`Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.`,match:{or:[{equals:"gemini-2.5-flash"},{equals:"gemini-2.5-flash-latest"},{equals:"gemini-2.5-flash-preview-09-2025"}]},prices:{input_mtok:.3,cache_read_mtok:.03,output_mtok:2.5,input_audio_mtok:1,cache_audio_read_mtok:.1}},{id:"gemini-2.5-flash-image",name:"Gemini 2.5 Flash Image",description:"Google's specialized image generation model optimized for fast, high-quality image generation. Outputs images at 1024x1024 resolution, with each image consuming 1290 output tokens.",match:{or:[{equals:"gemini-2.5-flash-image"},{equals:"gemini-2.5-flash-image-preview"}]},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image. Image output is priced at $30 per 1M tokens, with each 1024x1024 image = 1290 tokens = $0.039/image. Cache pricing is not available for this model.",prices:{input_mtok:.3,output_mtok:30}},{id:"gemini-2.5-flash-lite",name:"Gemini 2.5 Flash Lite",description:'Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.',match:{or:[{equals:"gemini-2.5-flash-lite"},{starts_with:"gemini-2.5-flash-lite-preview"}]},context_window:1e6,prices:{input_mtok:.1,cache_read_mtok:.01,output_mtok:.4,input_audio_mtok:.3,cache_audio_read_mtok:.03}},{id:"gemini-2.5-flash-preview",name:"Gemini 2.5 Flash Preview 05-20",description:`Gemini 2.5 Flash May 20th Checkpoint is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.`,match:{or:[{contains:"gemini-2.5-flash-preview-05-20"},{contains:"gemini-2.5-flash-preview-04-17"},{equals:"gemini-2.5-flash-preview-05-20:thinking"},{equals:"gemini-2.5-flash-preview"},{equals:"gemini-2.5-flash-preview:thinking"}]},price_comments:"from https://cloud.google.com/vertex-ai/generative-ai/pricing should be retired 2025-07-15",prices:{input_mtok:.15,output_mtok:.6},deprecated:!0},{id:"gemini-2.5-pro",name:"Gemini 2.5 Pro",description:`Gemini 2.5 Pro is Google's state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs "thinking" capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.`,match:{starts_with:"gemini-2.5-pro"},price_comments:"See https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro",prices:{input_mtok:{base:1.25,tiers:[{start:2e5,price:2.5}]},cache_read_mtok:{base:.125,tiers:[{start:2e5,price:.25}]},output_mtok:{base:10,tiers:[{start:2e5,price:15}]}}},{id:"gemini-3-flash-preview",name:"Gemini 3 Flash Preview",description:"Google's ultra-fast frontier model optimized for speed and efficiency. Delivers state-of-the-art performance while maintaining low latency and cost, with improved reasoning and coding capabilities.",match:{or:[{equals:"gemini-3-flash-preview"},{starts_with:"gemini-3-flash-preview-"}]},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing. Standard pricing shown; Batch API offers 50% discount on input/output.",prices:{input_mtok:.5,cache_read_mtok:.05,output_mtok:3,input_audio_mtok:1,cache_audio_read_mtok:.1}},{id:"gemini-3-pro-image-preview",name:"Gemini 3 Pro Image Preview",description:"Google's image generation model optimized for high-quality image generation. Supports 1K/2K and 4K resolution outputs with flexible pricing based on image dimensions.",match:{or:[{starts_with:"gemini-3-pro-image-preview"},{equals:"gemini-3-pro-image-preview"}]},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image. Image output is priced at $120 per 1M tokens, with each 1K/2K image = 1120 tokens = $0.134/image and each 4K image = 2000 tokens = $0.24/image.",prices:{input_mtok:2,output_mtok:120}},{id:"gemini-3-pro-preview",name:"Gemini 3 Pro Preview",description:"The best model in the world for multimodal understanding, and our most powerful agentic and vibe-coding model yet.",match:{or:[{starts_with:"gemini-3-pro-preview"},{equals:"gemini-3-pro-text-preview"}]},prices:{input_mtok:{base:2,tiers:[{start:2e5,price:4}]},cache_read_mtok:{base:.2,tiers:[{start:2e5,price:.4}]},output_mtok:{base:12,tiers:[{start:2e5,price:18}]}}},{id:"gemini-3.1-flash-image-preview",name:"Gemini 3.1 Flash Image Preview",description:"Google's latest image generation model (Nano Banana 2) optimized for fast, high-quality image generation. Supports multiple output resolutions from 512px to 4K, with text and thinking output priced separately from image output tokens.",match:{starts_with:"gemini-3.1-flash-image-preview"},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing. Image output is priced at $60 per 1M tokens. Preview model - pricing may change.",prices:{input_mtok:.5,output_mtok:60}},{id:"gemini-3.1-flash-lite",name:"Gemini 3.1 Flash Lite",description:"Google's fastest and most cost-efficient Gemini 3 series model, built for intelligence at scale. Optimized for high-volume, low-latency applications while maintaining strong multimodal capabilities.",match:{starts_with:"gemini-3.1-flash-lite"},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing.",prices:{input_mtok:.25,cache_read_mtok:.025,output_mtok:1.5,input_audio_mtok:.5,cache_audio_read_mtok:.05}},{id:"gemini-3.1-pro-preview",name:"Gemini 3.1 Pro Preview",description:"The latest performance, intelligence, and usability improvements to the best model family in the world for multimodal understanding, agentic capabilities, and vibe-coding.",match:{starts_with:"gemini-3.1-pro-preview"},prices:{input_mtok:{base:2,tiers:[{start:2e5,price:4}]},cache_read_mtok:{base:.2,tiers:[{start:2e5,price:.4}]},output_mtok:{base:12,tiers:[{start:2e5,price:18}]}}},{id:"gemini-3.5-flash",name:"Gemini 3.5 Flash",description:"Google's most intelligent model built for speed, combining frontier intelligence with improved reasoning, coding, and multimodal understanding.",match:{starts_with:"gemini-3.5-flash"},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing. Standard tier pricing shown; Batch and Flex tiers offer 50% discount on input/output.",prices:{input_mtok:1.5,cache_read_mtok:.15,output_mtok:9}},{id:"gemini-embedding-001",match:{equals:"gemini-embedding-001"},prices:{input_mtok:.15}},{id:"gemini-flash-1.5",name:"Gemini 1.5 Flash",description:"Gemini 1.5 Flash is a foundation model that performs well at a variety of multimodal tasks such as visual understanding, classification, summarization, and creating content from image, audio and video. It's adept at processing visual and text inputs such as photographs, documents, infographics, and screenshots.",match:{equals:"gemini-flash-1.5"},price_comments:"See https://ai.google.dev/gemini-api/docs/pricing#gemini-1.5-flash",prices:{input_mtok:{base:.075,tiers:[{start:128e3,price:.15}]},cache_read_mtok:{base:.01875,tiers:[{start:128e3,price:.0375}]},output_mtok:{base:.3,tiers:[{start:128e3,price:.6}]}}},{id:"gemini-flash-1.5-8b",name:"gemini 1.5 flash",description:"A faster, more cost-effective variant of Gemini 1.5 that maintains strong capabilities while optimizing for performance and cost efficiency. Suitable for production deployments requiring high throughput.",match:{equals:"gemini-flash-1.5-8b"},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing#gemini-1.5-flash-8b",prices:{input_mtok:{base:.0375,tiers:[{start:128e3,price:.075}]},cache_read_mtok:{base:.01,tiers:[{start:128e3,price:.02}]},output_mtok:{base:.15,tiers:[{start:128e3,price:.3}]}}},{id:"gemini-live-2.5-flash-preview",match:{or:[{starts_with:"gemini-live-2.5-flash-preview"},{starts_with:"gemini-2.5-flash-native-audio-preview"}]},prices:{input_mtok:.5,output_mtok:2,input_audio_mtok:3,output_audio_mtok:12}},{id:"gemini-pro",name:"gemini 1.0 pro",description:"Google's first-generation advanced multimodal model that can understand text, code, and images. It provides strong reasoning capabilities and follows instructions effectively.",match:{or:[{equals:"gemini-pro"},{equals:"gemini-1.0-pro"}]},context_window:32768,price_comments:"I can't find anything so trusting these prices, not sure the model still exists",prices:{input_mtok:.125,output_mtok:.375}},{id:"gemini-pro-1.5",name:"Gemini 1.5 Pro",description:"Google's latest multimodal model, supports image and video[0] in text or chat prompts.",match:{equals:"gemini-pro-1.5"},context_window:2e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing#gemini-1.5-pro",prices:{input_mtok:{base:1.25,tiers:[{start:128e3,price:2.5}]},cache_read_mtok:{base:.3125,tiers:[{start:128e3,price:.625}]},output_mtok:{base:5,tiers:[{start:128e3,price:10}]}}},{id:"gemma-3",name:"Gemma 3 (free)",description:"Lightweight, state-of the art, open model built from the same technology that powers our Gemini models.",match:{or:[{starts_with:"gemma-3-"},{equals:"gemma-3"}]},prices:{}},{id:"gemma-3n",name:"Gemma 3n (free)",description:"Our open model built for efficient performance on everyday devices like mobile phones, laptops, and tablets.",match:{or:[{starts_with:"gemma-3n"}]},prices:{}}]},{id:"groq",name:"Groq",pricing_urls:["https://groq.com/pricing/"],api_pattern:"https://api\\.groq\\.com",extractors:[{api_flavor:"default",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"deepseek-r1-distill-llama-70b",name:"DeepSeek R1 Distill Llama 70B",match:{equals:"deepseek-r1-distill-llama-70b"},context_window:131072,prices:{input_mtok:.75,output_mtok:.99}},{id:"gemma-7b-it",match:{equals:"gemma-7b-it"},prices:{input_mtok:.07,output_mtok:.07}},{id:"gemma2-9b-it",name:"Gemma 2 9B 8k",match:{or:[{equals:"gemma2-9b-it"},{equals:"gemma2-9b"}]},prices:{input_mtok:.2,output_mtok:.2}},{id:"llama-3.1-405b-reasoning",match:{equals:"llama-3.1-405b-reasoning"},prices:{input_mtok:.59,output_mtok:.79}},{id:"llama-3.1-70b-versatile",match:{equals:"llama-3.1-70b-versatile"},prices:{input_mtok:.59,output_mtok:.79}},{id:"llama-3.1-8b-instant",name:"Llama 3.1 8B Instant 128k",match:{equals:"llama-3.1-8b-instant"},prices:{input_mtok:.05,output_mtok:.08}},{id:"llama-3.2-11b-text-preview",match:{equals:"llama-3.2-11b-text-preview"},prices:{input_mtok:.18,output_mtok:.18}},{id:"llama-3.2-11b-vision-preview",match:{equals:"llama-3.2-11b-vision-preview"},prices:{input_mtok:.18,output_mtok:.18}},{id:"llama-3.2-1b-preview",match:{equals:"llama-3.2-1b-preview"},prices:{input_mtok:.04,output_mtok:.04}},{id:"llama-3.2-3b-preview",match:{equals:"llama-3.2-3b-preview"},prices:{input_mtok:.06,output_mtok:.06}},{id:"llama-3.2-90b-text-preview",match:{equals:"llama-3.2-90b-text-preview"},prices:{input_mtok:.9,output_mtok:.9}},{id:"llama-3.2-90b-vision-preview",match:{equals:"llama-3.2-90b-vision-preview"},prices:{input_mtok:.9,output_mtok:.9}},{id:"llama-3.3-70b-specdec",match:{equals:"llama-3.3-70b-specdec"},prices:{input_mtok:.59,output_mtok:.99}},{id:"llama-3.3-70b-versatile",name:"Llama 3.3 70B Versatile 128k",match:{equals:"llama-3.3-70b-versatile"},prices:{input_mtok:.59,output_mtok:.79}},{id:"llama-guard-3-8b",match:{equals:"llama-guard-3-8b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"llama2-70b-4096",match:{equals:"llama2-70b-4096"},prices:{input_mtok:.7,output_mtok:.8}},{id:"llama3-70b-8192",match:{equals:"llama3-70b-8192"},prices:{input_mtok:.59,output_mtok:.79}},{id:"llama3-8b-8192",match:{equals:"llama3-8b-8192"},prices:{input_mtok:.05,output_mtok:.08}},{id:"llama3-groq-70b-8192-tool-use-preview",match:{equals:"llama3-groq-70b-8192-tool-use-preview"},prices:{input_mtok:.89,output_mtok:.89}},{id:"llama3-groq-8b-8192-tool-use-preview",match:{equals:"llama3-groq-8b-8192-tool-use-preview"},prices:{input_mtok:.19,output_mtok:.19}},{id:"meta-llama/llama-4-maverick-17b-128e-instruct",name:"Llama 4 Maverick 17B 128E",match:{equals:"meta-llama/llama-4-maverick-17b-128e-instruct"},context_window:131072,prices:{input_mtok:.2,output_mtok:.6}},{id:"meta-llama/llama-4-scout-17b-16e-instruct",name:"Llama 4 Scout (17Bx16E) 128k",match:{equals:"meta-llama/llama-4-scout-17b-16e-instruct"},prices:{input_mtok:.11,output_mtok:.34}},{id:"meta-llama/llama-guard-4-12b",name:"Llama Guard 4 12B",match:{equals:"meta-llama/llama-guard-4-12b"},context_window:131072,prices:{input_mtok:.2,output_mtok:.2}},{id:"mistral-saba-24b",match:{equals:"mistral-saba-24b"},prices:{input_mtok:.79,output_mtok:.79}},{id:"mixtral-8x7b-32768",match:{equals:"mixtral-8x7b-32768"},prices:{input_mtok:.24,output_mtok:.24}},{id:"moonshotai/kimi-k2-instruct",name:"Kimi K2 1T 128k",match:{or:[{equals:"moonshotai/kimi-k2-instruct"},{equals:"moonshotai/kimi-k2-instruct-0905"}]},context_window:131072,prices:{input_mtok:1,cache_read_mtok:.5,output_mtok:3}},{id:"openai/gpt-oss-120b",description:`GPT-OSS 120B is OpenAI's flagship open source model, built on a Mixture-of-Experts (MoE) architecture with
1
+ "use strict";Object.defineProperty(exports,Symbol.toStringTag,{value:"Module"});const G=[{id:"anthropic",name:"Anthropic",pricing_urls:["https://www.anthropic.com/pricing#api"],api_pattern:"https://api\\.anthropic\\.com",model_match:{contains:"claude"},provider_match:{contains:"anthropic"},extractors:[{api_flavor:"default",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:"cache_creation_input_tokens",dest:"input_tokens",required:!1},{path:"cache_read_input_tokens",dest:"input_tokens",required:!1},{path:"cache_creation_input_tokens",dest:"cache_write_tokens",required:!1},{path:"cache_read_input_tokens",dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:"cached_tokens",dest:"cache_read_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"claude-2",name:"Claude 2.0 / 2.1",description:`Claude 2 is Anthropic's previous generation model, offering reliable performance for various tasks. This includes Claude 2.0 and Claude 2.1.
2
+ `,match:{or:[{starts_with:"claude-2"},{contains:"claude-v2"}]},context_window:2e5,prices:{input_mtok:8,output_mtok:24}},{id:"claude-3-5-haiku-latest",name:"Claude Haiku 3.5",description:"Fastest, most cost-effective model",match:{or:[{starts_with:"claude-3-5-haiku"},{starts_with:"claude-3.5-haiku"}]},context_window:2e5,prices:{input_mtok:.8,cache_write_mtok:1,cache_read_mtok:.08,output_mtok:4}},{id:"claude-3-5-sonnet",name:"Claude Sonnet 3.5",description:"Claude 3.5 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments.",match:{or:[{starts_with:"claude-3-5-sonnet"},{starts_with:"claude-3.5-sonnet"}]},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-3-7-sonnet-latest",name:"Claude Sonnet 3.7",description:"Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities.",match:{or:[{starts_with:"claude-3-7-sonnet"},{starts_with:"claude-3.7-sonnet"},{starts_with:"claude-sonnet-3.7"},{starts_with:"claude-sonnet-3-7"}]},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-3-haiku",name:"Claude Haiku 3",description:"Fastest, most cost-effective model",match:{starts_with:"claude-3-haiku"},context_window:2e5,prices:{input_mtok:.25,cache_write_mtok:.3,cache_read_mtok:.03,output_mtok:1.25}},{id:"claude-3-opus-latest",name:"Claude Opus 3",description:"Claude 3 Opus was Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding.",match:{starts_with:"claude-3-opus"},context_window:2e5,prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"claude-3-sonnet",name:"Claude 3 Sonnet",description:"Claude 3 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments.",match:{starts_with:"claude-3-sonnet"},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-fable-5",name:"Claude Fable 5",description:"Anthropic's most capable widely released model for demanding reasoning and long-horizon agentic work",match:{starts_with:"claude-fable-5"},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:10,cache_write_mtok:12.5,cache_read_mtok:1,output_mtok:50}},{id:"claude-haiku-4-5",name:"Claude Haiku 4.5",description:"Fastest and most intelligent Haiku model",match:{or:[{starts_with:"claude-haiku-4-5"},{starts_with:"claude-haiku-4.5"},{starts_with:"claude-4-5-haiku"},{starts_with:"claude-4.5-haiku"}]},context_window:2e5,prices:{input_mtok:1,cache_write_mtok:1.25,cache_read_mtok:.1,output_mtok:5}},{id:"claude-opus-4-0",name:"Claude Opus 4",description:"Most intelligent model for complex tasks",match:{or:[{starts_with:"claude-opus-4-0"},{starts_with:"claude-4-opus"},{equals:"claude-opus-4"},{equals:"claude-opus-4-20250514"}]},context_window:2e5,prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"claude-opus-4-1",name:"Claude Opus 4.1",description:"Most intelligent model for complex tasks",match:{or:[{starts_with:"claude-opus-4-1"},{starts_with:"claude-opus-4.1"}]},context_window:2e5,prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"claude-opus-4-5",name:"Claude Opus 4.5",description:"Premium model combining maximum intelligence with practical performance",match:{or:[{starts_with:"claude-opus-4-5"},{starts_with:"claude-opus-4.5"},{starts_with:"claude-4-5-opus"},{starts_with:"claude-4.5-opus"}]},context_window:2e5,prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"claude-opus-4-6",name:"Claude Opus 4.6",description:"Our most intelligent model for building agents and coding",match:{or:[{starts_with:"claude-opus-4-6"},{starts_with:"claude-opus-4.6"},{starts_with:"claude-4-6-opus"},{starts_with:"claude-4.6-opus"}]},context_window:2e5,prices:[{prices:{input_mtok:{base:5,tiers:[{start:2e5,price:10}]},cache_write_mtok:{base:6.25,tiers:[{start:2e5,price:12.5}]},cache_read_mtok:{base:.5,tiers:[{start:2e5,price:1}]},output_mtok:{base:25,tiers:[{start:2e5,price:37.5}]}}},{constraint:{start_date:"2026-03-13",type:"start_date"},prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}}]},{id:"claude-opus-4-7",name:"Claude Opus 4.7",description:"Our most capable model for complex reasoning and agentic coding",match:{or:[{starts_with:"claude-opus-4-7"},{starts_with:"claude-opus-4.7"},{starts_with:"claude-4-7-opus"},{starts_with:"claude-4.7-opus"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"claude-opus-4-8",name:"Claude Opus 4.8",description:"Our most capable model for complex reasoning and agentic coding",match:{or:[{starts_with:"claude-opus-4-8"},{starts_with:"claude-opus-4.8"},{starts_with:"claude-4-8-opus"},{starts_with:"claude-4.8-opus"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"claude-sonnet-4-0",name:"Claude Sonnet 4",description:"Optimal balance of intelligence, cost, and speed",match:{or:[{starts_with:"claude-sonnet-4-2025"},{starts_with:"claude-sonnet-4-0"},{starts_with:"claude-sonnet-4@"},{equals:"claude-sonnet-4"},{starts_with:"claude-4-sonnet"}]},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-sonnet-4-5",name:"Claude Sonnet 4.5",description:"Our best combination of speed and intelligence",match:{or:[{starts_with:"claude-sonnet-4-5"},{starts_with:"claude-sonnet-4.5"}]},context_window:1e6,prices:{input_mtok:{base:3,tiers:[{start:2e5,price:6}]},cache_write_mtok:{base:3.75,tiers:[{start:2e5,price:7.5}]},cache_read_mtok:{base:.3,tiers:[{start:2e5,price:.6}]},output_mtok:{base:15,tiers:[{start:2e5,price:22.5}]}}},{id:"claude-sonnet-4-6",name:"Claude Sonnet 4.6",description:"Our best combination of speed and intelligence",match:{or:[{starts_with:"claude-sonnet-4-6"},{starts_with:"claude-sonnet-4.6"}]},context_window:1e6,prices:[{prices:{input_mtok:{base:3,tiers:[{start:2e5,price:6}]},cache_write_mtok:{base:3.75,tiers:[{start:2e5,price:7.5}]},cache_read_mtok:{base:.3,tiers:[{start:2e5,price:.6}]},output_mtok:{base:15,tiers:[{start:2e5,price:22.5}]}}},{constraint:{start_date:"2026-03-13",type:"start_date"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}}]},{id:"claude-v1",description:"Retired, here to match price sources",match:{equals:"claude-v1"},prices:{input_mtok:8,output_mtok:24}}]},{id:"avian",name:"Avian",pricing_urls:["https://avian.io/pricing/"],api_pattern:"https://api\\.avian\\.io",models:[{id:"Meta-Llama-3.1-405B-Instruct",match:{equals:"Meta-Llama-3.1-405B-Instruct"},prices:{input_mtok:1.5,output_mtok:1.5}},{id:"Meta-Llama-3.1-70B-Instruct",match:{equals:"Meta-Llama-3.1-70B-Instruct"},prices:{input_mtok:.45,output_mtok:.45}},{id:"Meta-Llama-3.1-8B-Instruct",match:{equals:"Meta-Llama-3.1-8B-Instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"Meta-Llama-3.3-70B-Instruct",match:{equals:"Meta-Llama-3.3-70B-Instruct"},prices:{input_mtok:.45,output_mtok:.45}}]},{id:"aws",name:"AWS Bedrock",pricing_urls:["https://aws.amazon.com/bedrock/pricing/"],api_pattern:"https://bedrock-runtime\\.[a-z0-9-]+\\.amazonaws\\.com/",provider_match:{or:[{contains:"bedrock"},{contains:"amazon"}]},extractors:[{api_flavor:"default",root:"usage",model_path:"model",mappings:[{path:"inputTokens",dest:"input_tokens",required:!0},{path:"outputTokens",dest:"output_tokens",required:!0}]},{api_flavor:"anthropic",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:"cache_creation_input_tokens",dest:"input_tokens",required:!1},{path:"cache_read_input_tokens",dest:"input_tokens",required:!1},{path:"cache_creation_input_tokens",dest:"cache_write_tokens",required:!1},{path:"cache_read_input_tokens",dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"amazon.nova-2-sonic-v1:0",name:"Nova 2 Sonic",match:{contains:"amazon.nova-2-sonic"},prices:{input_mtok:.33,output_mtok:2.75,input_audio_mtok:3,output_audio_mtok:12}},{id:"amazon.nova-lite-v1:0",name:"Nova Lite",description:"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy.",match:{contains:"amazon.nova-lite"},prices:{input_mtok:.06,cache_read_mtok:.015,output_mtok:.24}},{id:"amazon.nova-micro-v1:0",name:"Nova Micro",description:"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for speed and cost, Amazon Nova Micro excels at tasks such as text summarization, translation, content classification, interactive chat, and brainstorming. It has simple mathematical reasoning and coding abilities.",match:{contains:"amazon.nova-micro"},prices:{input_mtok:.035,cache_read_mtok:.00875,output_mtok:.14}},{id:"amazon.nova-premier-v1:0",name:"Nova Premier",match:{contains:"amazon.nova-premier"},prices:{input_mtok:2.5,cache_read_mtok:.625,output_mtok:12.5}},{id:"amazon.nova-pro-v1:0",name:"Nova Pro",description:"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on key benchmarks including visual question answering (TextVQA) and video understanding (VATEX).",match:{contains:"amazon.nova-pro"},prices:{input_mtok:.8,cache_read_mtok:.2,output_mtok:3.2}},{id:"amazon.nova-sonic-v1:0",name:"Nova Sonic",match:{contains:"amazon.nova-sonic"},prices:{input_mtok:.06,output_mtok:.24,input_audio_mtok:3.4,output_audio_mtok:13.6}},{id:"amazon.titan-embed-text-v1",name:"Titan Embeddings G1 - Text",match:{contains:"amazon.titan-embed-text"},prices:{input_mtok:.1}},{id:"amazon.titan-text-express-v1",name:"Titan Text G1 - Express",match:{contains:"titan-text-express"},prices:{input_mtok:.2,output_mtok:.6}},{id:"amazon.titan-text-lite-v1",name:"Titan Text G1 - Lite",match:{contains:"titan-text-lite"},prices:{input_mtok:.15,output_mtok:.2}},{id:"deepseek.r1-v1:0",name:"DeepSeek-R1",match:{contains:"deepseek.r1"},prices:{input_mtok:1.35,output_mtok:5.4}},{id:"global.amazon.nova-2-lite-v1:0",name:"Nova 2 Lite",match:{contains:"global.amazon.nova-2-lite"},prices:{input_mtok:.3,cache_read_mtok:.075,output_mtok:2.5}},{id:"global.anthropic.claude-fable-5-v1:0",match:{contains:"global.anthropic.claude-fable-5"},prices:{input_mtok:10,cache_write_mtok:12.5,cache_read_mtok:1,output_mtok:50}},{id:"global.anthropic.claude-haiku-4-5-20251001-v1:0",match:{contains:"global.anthropic.claude-haiku-4-5-20251001"},prices:{input_mtok:1,cache_write_mtok:1.25,cache_read_mtok:.1,output_mtok:5}},{id:"global.anthropic.claude-opus-4-5-v1:0",match:{contains:"global.anthropic.claude-opus-4-5"},prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"global.anthropic.claude-opus-4-6-v1:0",match:{contains:"global.anthropic.claude-opus-4-6"},prices:{input_mtok:{base:5,tiers:[{start:2e5,price:10}]},cache_write_mtok:{base:6.25,tiers:[{start:2e5,price:12.5}]},cache_read_mtok:{base:.5,tiers:[{start:2e5,price:1}]},output_mtok:{base:25,tiers:[{start:2e5,price:37.5}]}}},{id:"global.anthropic.claude-opus-4-7-v1:0",match:{contains:"global.anthropic.claude-opus-4-7"},prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"global.anthropic.claude-opus-4-8-v1:0",match:{contains:"global.anthropic.claude-opus-4-8"},prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"global.anthropic.claude-sonnet-4-20250514-v1:0",match:{contains:"global.anthropic.claude-sonnet-4-20250514"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"global.anthropic.claude-sonnet-4-5-20250929-v1:0",match:{contains:"global.anthropic.claude-sonnet-4-5-20250929"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"global.anthropic.claude-sonnet-4-6-v1:0",match:{contains:"global.anthropic.claude-sonnet-4-6"},prices:{input_mtok:{base:3,tiers:[{start:2e5,price:6}]},cache_write_mtok:{base:3.75,tiers:[{start:2e5,price:7.5}]},cache_read_mtok:{base:.3,tiers:[{start:2e5,price:.6}]},output_mtok:{base:15,tiers:[{start:2e5,price:22.5}]}}},{id:"google.gemma-3-12b-it",name:"Gemma 3 12B IT",match:{contains:"google.gemma-3-12b-it"},prices:{input_mtok:.09,output_mtok:.29}},{id:"google.gemma-3-27b-it",name:"Gemma 3 27B IT",match:{contains:"google.gemma-3-27b-it"},prices:{input_mtok:.23,output_mtok:.38}},{id:"google.gemma-3-4b-it",name:"Gemma 3 4B IT",match:{contains:"google.gemma-3-4b-it"},prices:{input_mtok:.04,output_mtok:.08}},{id:"meta.llama3-1-70b-instruct-v1:0",name:"Llama 3.1 70B Instruct",match:{contains:"meta.llama3-1-70b-instruct"},prices:{input_mtok:.72,output_mtok:.72}},{id:"meta.llama3-1-8b-instruct-v1:0",name:"Llama 3.1 8B Instruct",match:{contains:"meta.llama3-1-8b-instruct"},prices:{input_mtok:.22,output_mtok:.22}},{id:"meta.llama3-2-11b-instruct-v1:0",name:"Llama 3.2 11B Instruct",match:{contains:"meta.llama3-2-11b-instruct"},prices:{input_mtok:.16,output_mtok:.16}},{id:"meta.llama3-2-1b-instruct-v1:0",name:"Llama 3.2 1B Instruct",match:{contains:"meta.llama3-2-1b-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"meta.llama3-2-3b-instruct-v1:0",name:"Llama 3.2 3B Instruct",match:{contains:"meta.llama3-2-3b-instruct"},prices:{input_mtok:.15,output_mtok:.15}},{id:"meta.llama3-2-90b-instruct-v1:0",name:"Llama 3.2 90B Instruct",match:{contains:"meta.llama3-2-90b-instruct"},prices:{input_mtok:.72,output_mtok:.72}},{id:"meta.llama3-3-70b-instruct-v1:0",name:"Llama 3.3 70B Instruct",match:{contains:"meta.llama3-3-70b-instruct"},prices:{input_mtok:.72,output_mtok:.72}},{id:"meta.llama3-70b-instruct-v1:0",name:"Llama 3 70B Instruct",match:{contains:"meta.llama3-70b-instruct"},prices:{input_mtok:2.65,output_mtok:3.5}},{id:"meta.llama3-8b-instruct-v1:0",name:"Llama 3 8B Instruct",match:{contains:"meta.llama3-8b-instruct"},prices:{input_mtok:.3,output_mtok:.6}},{id:"meta.llama4-maverick-17b-instruct-v1:0",name:"Llama 4 Maverick 17B Instruct",match:{contains:"meta.llama4-maverick-17b-instruct"},prices:{input_mtok:.24,output_mtok:.97}},{id:"meta.llama4-scout-17b-instruct-v1:0",name:"Llama 4 Scout 17B Instruct",match:{contains:"meta.llama4-scout-17b-instruct"},prices:{input_mtok:.17,output_mtok:.66}},{id:"mistral.devstral-2-123b",name:"Devstral 2 123B",match:{contains:"mistral.devstral-2-123b"},prices:{input_mtok:.4,output_mtok:2}},{id:"mistral.magistral-small-2509",name:"Magistral Small 2509",match:{contains:"mistral.magistral-small-2509"},prices:{input_mtok:.5,output_mtok:1.5}},{id:"mistral.ministral-3-14b-instruct",name:"Ministral 14B 3.0",match:{contains:"mistral.ministral-3-14b-instruct"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistral.ministral-3-3b-instruct",name:"Ministral 3B 3.0",match:{contains:"mistral.ministral-3-3b-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistral.ministral-3-8b-instruct",name:"Ministral 8B 3.0",match:{contains:"mistral.ministral-3-8b-instruct"},prices:{input_mtok:.15,output_mtok:.15}},{id:"mistral.mistral-7b-instruct-v0:2",name:"Mistral 7B Instruct",match:{contains:"mistral.mistral-7b-instruct-v0"},prices:{input_mtok:.15,output_mtok:.2}},{id:"mistral.mistral-large-2402-v1:0",name:"Mistral Large (24.02)",match:{contains:"mistral.mistral-large-2402"},prices:{input_mtok:4,output_mtok:12}},{id:"mistral.mistral-large-3-675b-instruct",name:"Mistral Large 3",match:{contains:"mistral.mistral-large-3-675b-instruct"},prices:{input_mtok:.5,output_mtok:1.5}},{id:"mistral.mistral-small-2402-v1:0",name:"Mistral Small (24.02)",match:{contains:"mistral.mistral-small-2402"},prices:{input_mtok:1,output_mtok:3}},{id:"mistral.mixtral-8x7b-instruct-v0:1",name:"Mixtral 8x7B Instruct",match:{contains:"mistral.mixtral-8x7b-instruct-v0"},prices:{input_mtok:.45,output_mtok:.7}},{id:"mistral.pixtral-large-2502-v1:0",name:"Pixtral Large (25.02)",match:{contains:"mistral.pixtral-large-2502"},prices:{input_mtok:2,output_mtok:6}},{id:"mistral.voxtral-mini-3b-2507",name:"Voxtral Mini 3B 2507",match:{contains:"mistral.voxtral-mini-3b-2507"},prices:{input_mtok:.04,output_mtok:.04}},{id:"mistral.voxtral-small-24b-2507",name:"Voxtral Small 24B 2507",match:{contains:"mistral.voxtral-small-24b-2507"},prices:{input_mtok:.1,output_mtok:.3}},{id:"nvidia.nemotron-nano-3-30b:0",name:"Nemotron 3 Nano 30B",match:{contains:"nvidia.nemotron-nano-3-30b"},prices:{input_mtok:.06,output_mtok:.24}},{id:"nvidia.nemotron-nano-9b-v2:0",name:"Nemotron 2 Nano 9B",match:{contains:"nvidia.nemotron-nano-9b-v2"},prices:{input_mtok:.06,output_mtok:.23}},{id:"nvidia.nemotron-super-3-120b:0",name:"Nemotron 3 Super 120B",match:{contains:"nvidia.nemotron-super-3-120b"},prices:{input_mtok:.15,output_mtok:.65}},{id:"openai.gpt-oss-120b-1:0",name:"gpt-oss-120b",match:{contains:"openai.gpt-oss-120b-1"},prices:{input_mtok:.15,output_mtok:.6}},{id:"openai.gpt-oss-20b-1:0",name:"gpt-oss-20b",match:{contains:"openai.gpt-oss-20b-1"},prices:{input_mtok:.07,output_mtok:.3}},{id:"qwen.qwen3-32b-v1:0",name:"Qwen3 32B (dense)",match:{contains:"qwen.qwen3-32b"},prices:{input_mtok:.15,output_mtok:.6}},{id:"qwen.qwen3-coder-30b-a3b-v1:0",name:"Qwen3-Coder-30B-A3B-Instruct",match:{contains:"qwen.qwen3-coder-30b-a3b"},prices:{input_mtok:.15,output_mtok:.6}},{id:"qwen.qwen3-coder-480b-a35b-v1:0",name:"Qwen3-Coder-480B-A35B-Instruct",match:{contains:"qwen.qwen3-coder-480b-a35b"},prices:{input_mtok:.45,output_mtok:1.8}},{id:"qwen.qwen3-vl-235b-a22b-v1:0",name:"Qwen3-VL-235B-A22B-Instruct",match:{contains:"qwen.qwen3-vl-235b-a22b"},prices:{input_mtok:.53,output_mtok:2.66}},{id:"regional.amazon.nova-2-lite-v1:0",name:"Nova 2 Lite",description:"Amazon Nova 2 Lite is an advanced multimodal reasoning model that intelligently balances performance and efficiency by dynamically adjusting reasoning depth based on task complexity. With flexible controls for developers to adjust the reasoning process, Nova 2 Lite delivers superior results for agentic workflows across software development, consumer experiences and enterprise application.",match:{or:[{contains:"us.amazon.nova-2-lite"},{contains:"eu.amazon.nova-2-lite"},{contains:"jp.amazon.nova-2-lite"}]},prices:{input_mtok:.33,cache_read_mtok:.0825,output_mtok:2.75}},{id:"regional.anthropic.claude-3-5-haiku-20241022-v1:0",match:{contains:"claude-3-5-haiku-20241022"},prices:{input_mtok:.8,cache_write_mtok:1,cache_read_mtok:.08,output_mtok:4}},{id:"regional.anthropic.claude-3-5-sonnet-20240620-v1:0",match:{contains:"claude-3-5-sonnet-20240620"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"regional.anthropic.claude-3-5-sonnet-20241022-v2:0",match:{contains:"claude-3-5-sonnet-20241022"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"regional.anthropic.claude-3-7-sonnet-20250219-v1:0",match:{contains:"claude-3-7-sonnet-20250219"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"regional.anthropic.claude-3-haiku-20240307-v1:0",match:{contains:"claude-3-haiku-20240307"},prices:{input_mtok:.25,output_mtok:1.25}},{id:"regional.anthropic.claude-3-opus-20240229-v1:0",match:{contains:"claude-3-opus-20240229"},prices:{input_mtok:15,output_mtok:75}},{id:"regional.anthropic.claude-3-sonnet-20240229-v1:0",match:{contains:"claude-3-sonnet-20240229"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"regional.anthropic.claude-fable-5-v1:0",match:{or:[{starts_with:"anthropic.claude-fable-5"},{starts_with:"claude-fable-5"},{contains:"us.anthropic.claude-fable-5"},{contains:"au.anthropic.claude-fable-5"},{contains:"eu.anthropic.claude-fable-5"},{contains:"jp.anthropic.claude-fable-5"}]},prices:{input_mtok:11,cache_write_mtok:13.75,cache_read_mtok:1.1,output_mtok:55}},{id:"regional.anthropic.claude-haiku-4-5-20251001-v1:0",match:{or:[{starts_with:"anthropic.claude-haiku-4-5-20251001"},{starts_with:"claude-haiku-4-5-20251001"},{contains:"us.anthropic.claude-haiku-4-5-20251001"},{contains:"au.anthropic.claude-haiku-4-5-20251001"},{contains:"apac.anthropic.claude-haiku-4-5-20251001"},{contains:"eu.anthropic.claude-haiku-4-5-20251001"},{contains:"us-gov.anthropic.claude-haiku-4-5-20251001"},{contains:"jp.anthropic.claude-haiku-4-5-20251001"}]},prices:{input_mtok:1.1,cache_write_mtok:1.375,cache_read_mtok:.11,output_mtok:5.5}},{id:"regional.anthropic.claude-opus-4-1-20250805-v1:0",match:{or:[{starts_with:"anthropic.claude-opus-4-1-20250805"},{starts_with:"claude-opus-4-1-20250805"},{contains:"us.anthropic.claude-opus-4-1-20250805"},{contains:"au.anthropic.claude-opus-4-1-20250805"},{contains:"apac.anthropic.claude-opus-4-1-20250805"},{contains:"eu.anthropic.claude-opus-4-1-20250805"},{contains:"us-gov.anthropic.claude-opus-4-1-20250805"},{contains:"jp.anthropic.claude-opus-4-1-20250805"}]},prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"regional.anthropic.claude-opus-4-20250514-v1:0",match:{or:[{starts_with:"anthropic.claude-opus-4-20250514"},{starts_with:"claude-opus-4-20250514"},{contains:"us.anthropic.claude-opus-4-20250514"},{contains:"au.anthropic.claude-opus-4-20250514"},{contains:"apac.anthropic.claude-opus-4-20250514"},{contains:"eu.anthropic.claude-opus-4-20250514"},{contains:"us-gov.anthropic.claude-opus-4-20250514"},{contains:"jp.anthropic.claude-opus-4-20250514"}]},prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"regional.anthropic.claude-opus-4-5-v1:0",match:{or:[{starts_with:"anthropic.claude-opus-4-5"},{starts_with:"claude-opus-4-5"},{contains:"us.anthropic.claude-opus-4-5"},{contains:"au.anthropic.claude-opus-4-5"},{contains:"apac.anthropic.claude-opus-4-5"},{contains:"eu.anthropic.claude-opus-4-5"},{contains:"us-gov.anthropic.claude-opus-4-5"},{contains:"jp.anthropic.claude-opus-4-5"}]},prices:{input_mtok:5.5,cache_write_mtok:6.875,cache_read_mtok:.55,output_mtok:27.5}},{id:"regional.anthropic.claude-opus-4-6-v1:0",match:{or:[{starts_with:"anthropic.claude-opus-4-6"},{starts_with:"claude-opus-4-6"},{contains:"us.anthropic.claude-opus-4-6"},{contains:"au.anthropic.claude-opus-4-6"},{contains:"apac.anthropic.claude-opus-4-6"},{contains:"eu.anthropic.claude-opus-4-6"},{contains:"us-gov.anthropic.claude-opus-4-6"},{contains:"jp.anthropic.claude-opus-4-6"}]},prices:{input_mtok:{base:5.5,tiers:[{start:2e5,price:11}]},cache_write_mtok:{base:6.875,tiers:[{start:2e5,price:13.75}]},cache_read_mtok:{base:.55,tiers:[{start:2e5,price:1.1}]},output_mtok:{base:27.5,tiers:[{start:2e5,price:41.25}]}}},{id:"regional.anthropic.claude-opus-4-7-v1:0",match:{or:[{starts_with:"anthropic.claude-opus-4-7"},{starts_with:"claude-opus-4-7"},{contains:"us.anthropic.claude-opus-4-7"},{contains:"au.anthropic.claude-opus-4-7"},{contains:"apac.anthropic.claude-opus-4-7"},{contains:"eu.anthropic.claude-opus-4-7"},{contains:"us-gov.anthropic.claude-opus-4-7"},{contains:"jp.anthropic.claude-opus-4-7"}]},prices:{input_mtok:5.5,cache_write_mtok:6.875,cache_read_mtok:.55,output_mtok:27.5}},{id:"regional.anthropic.claude-opus-4-8-v1:0",match:{or:[{starts_with:"anthropic.claude-opus-4-8"},{starts_with:"claude-opus-4-8"},{contains:"us.anthropic.claude-opus-4-8"},{contains:"au.anthropic.claude-opus-4-8"},{contains:"eu.anthropic.claude-opus-4-8"},{contains:"jp.anthropic.claude-opus-4-8"}]},prices:{input_mtok:5.5,cache_write_mtok:6.875,cache_read_mtok:.55,output_mtok:27.5}},{id:"regional.anthropic.claude-sonnet-4-20250514-v1:0",match:{or:[{starts_with:"anthropic.claude-sonnet-4-20250514"},{starts_with:"claude-sonnet-4-20250514"},{contains:"us.anthropic.claude-sonnet-4-20250514"},{contains:"au.anthropic.claude-sonnet-4-20250514"},{contains:"apac.anthropic.claude-sonnet-4-20250514"},{contains:"eu.anthropic.claude-sonnet-4-20250514"},{contains:"us-gov.anthropic.claude-sonnet-4-20250514"},{contains:"jp.anthropic.claude-sonnet-4-20250514"}]},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"regional.anthropic.claude-sonnet-4-5-20250929-v1:0",match:{or:[{starts_with:"anthropic.claude-sonnet-4-5-20250929"},{starts_with:"claude-sonnet-4-5-20250929"},{contains:"us.anthropic.claude-sonnet-4-5-20250929"},{contains:"au.anthropic.claude-sonnet-4-5-20250929"},{contains:"apac.anthropic.claude-sonnet-4-5-20250929"},{contains:"eu.anthropic.claude-sonnet-4-5-20250929"},{contains:"us-gov.anthropic.claude-sonnet-4-5-20250929"},{contains:"jp.anthropic.claude-sonnet-4-5-20250929"}]},prices:{input_mtok:3.3,cache_write_mtok:4.125,cache_read_mtok:.33,output_mtok:16.5}},{id:"regional.anthropic.claude-sonnet-4-6-v1:0",match:{or:[{starts_with:"anthropic.claude-sonnet-4-6"},{starts_with:"claude-sonnet-4-6"},{contains:"us.anthropic.claude-sonnet-4-6"},{contains:"au.anthropic.claude-sonnet-4-6"},{contains:"apac.anthropic.claude-sonnet-4-6"},{contains:"eu.anthropic.claude-sonnet-4-6"},{contains:"us-gov.anthropic.claude-sonnet-4-6"},{contains:"jp.anthropic.claude-sonnet-4-6"}]},prices:{input_mtok:{base:3.3,tiers:[{start:2e5,price:6.6}]},cache_write_mtok:{base:4.125,tiers:[{start:2e5,price:8.25}]},cache_read_mtok:{base:.33,tiers:[{start:2e5,price:.66}]},output_mtok:{base:16.5,tiers:[{start:2e5,price:24.75}]}}}]},{id:"azure",name:"Microsoft Azure",pricing_urls:["https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/#pricing"],api_pattern:"(https?://)?([^.]*\\.)?(?:openai\\.azure\\.com|azure-api\\.net|cognitiveservices\\.azure\\.com)",price_comments:'These are prices for "*-Global" models, prices for "Regional" models are often slightly higher. Retired models are listed at https://learn.microsoft.com/th-th/azure/ai-foundry/openai/concepts/legacy-models',extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"responses",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:["input_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"embeddings",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0}]},{api_flavor:"anthropic",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:"cache_creation_input_tokens",dest:"input_tokens",required:!1},{path:"cache_read_input_tokens",dest:"input_tokens",required:!1},{path:"cache_creation_input_tokens",dest:"cache_write_tokens",required:!1},{path:"cache_read_input_tokens",dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]}],fallback_model_providers:["openai","anthropic"],models:[{id:"ada",match:{or:[{equals:"ada"},{equals:"text-embedding-ada"},{equals:"text-embedding-ada-002"},{equals:"text-embedding-ada-002-v2"}]},prices:{input_mtok:.1}},{id:"babbage",match:{or:[{equals:"babbage"},{equals:"babbage-002"}]},prices:{input_mtok:.4}},{id:"curie",match:{or:[{equals:"curie"},{equals:"text-curie"},{equals:"text-curie-001"}]},prices:{input_mtok:2}},{id:"davinci",match:{or:[{equals:"davinci"},{equals:"davinci-002"},{equals:"text-davinci"},{equals:"text-davinci-002"}]},prices:{input_mtok:2}},{id:"mai-ds-r1:free",name:"MAI DS R1 (free)",description:"MAI-DS-R1 is a post-trained variant of DeepSeek-R1 developed by the Microsoft AI team to improve the model's responsiveness on previously blocked topics while enhancing its safety profile. Built on top of DeepSeek-R1's reasoning foundation, it integrates 110k examples from the Tulu-3 SFT dataset and 350k internally curated multilingual safety-alignment samples. The model retains strong reasoning, coding, and problem-solving capabilities, while unblocking a wide range of prompts previously restricted in R1.",match:{equals:"mai-ds-r1:free"},prices:{}},{id:"o1",match:{or:[{equals:"o1"},{equals:"o1-2024-12-17"},{equals:"o1-preview"},{equals:"o1-preview-2024-09-12"}]},prices:{input_mtok:15,cache_read_mtok:7.5,output_mtok:60}},{id:"o1-mini",match:{or:[{equals:"o1-mini"},{equals:"o1-mini-2024-09-12"}]},prices:{input_mtok:1.1,cache_read_mtok:.55,output_mtok:4.4}},{id:"o3-2025-04-16",match:{or:[{equals:"o3"},{equals:"o3-2025-04-16"}]},prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}},{id:"o3-mini",match:{or:[{equals:"o3-mini"},{equals:"o3-mini-2025-01-31"}]},prices:{input_mtok:1.1,cache_read_mtok:.55,output_mtok:4.4}},{id:"o4-mini",match:{or:[{contains:"o4-mini"},{contains:"o4-mini-2025-04-16"}]},prices:{input_mtok:1.1,cache_read_mtok:.28,output_mtok:4.4}},{id:"phi-3-medium-128k-instruct",name:"Phi-3 Medium 128K Instruct",description:"Phi-3 128K Medium is a powerful 14-billion parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference adjustments, it excels in tasks involving common sense, mathematics, logical reasoning, and code processing.",match:{equals:"phi-3-medium-128k-instruct"},prices:{input_mtok:1,output_mtok:1}},{id:"phi-3-mini-128k-instruct",name:"Phi-3 Mini 128K Instruct",description:"Phi-3 Mini is a powerful 3.8B parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference adjustments, it excels in tasks involving common sense, mathematics, logical reasoning, and code processing.",match:{equals:"phi-3-mini-128k-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"phi-3.5-mini-128k-instruct",name:"Phi-3.5 Mini 128K Instruct",description:"Phi-3.5 models are lightweight, state-of-the-art open models. These models were trained with Phi-3 datasets that include both synthetic data and the filtered, publicly available websites data, with a focus on high quality and reasoning-dense properties. Phi-3.5 Mini uses 3.8B parameters, and is a dense decoder-only transformer model using the same tokenizer as Phi-3 Mini.",match:{equals:"phi-3.5-mini-128k-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"phi-4",name:"Phi 4",description:"Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed.",match:{equals:"phi-4"},prices:{input_mtok:.07,output_mtok:.14}},{id:"phi-4-mini-instruct",name:"Phi 4 Mini Instruct",description:"Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites, with a focus on high-quality, reasoning-dense data.",match:{equals:"phi-4-mini-instruct"},price_comments:"Imported from OpenRouter pricing; verify against Azure AI Foundry when native pricing is published.",prices:{input_mtok:.08,cache_read_mtok:.08,output_mtok:.35}},{id:"phi-4-multimodal-instruct",name:"Phi 4 Multimodal Instruct",description:"Phi-4 Multimodal Instruct is a versatile 5.6B parameter foundation model that combines advanced reasoning and instruction-following capabilities across both text and visual inputs, providing accurate text outputs. The unified architecture enables efficient, low-latency inference, suitable for edge and mobile deployments. Phi-4 Multimodal Instruct supports text inputs in multiple languages including Arabic, Chinese, English, French, German, Japanese, Spanish, and more, with visual input optimized primarily for English. It delivers impressive performance on multimodal tasks involving mathematical, scientific, and document reasoning, providing developers and enterprises a powerful yet compact model for sophisticated interactive applications. For more information, see the Phi-4 Multimodal blog post.",match:{equals:"phi-4-multimodal-instruct"},prices:{input_mtok:.05,output_mtok:.1}},{id:"phi-4-reasoning-plus",name:"Phi 4 Reasoning Plus",description:"Phi-4-reasoning-plus is an enhanced 14B parameter model from Microsoft, fine-tuned from Phi-4 with additional reinforcement learning to boost accuracy on math, science, and code reasoning tasks. It uses the same dense decoder-only transformer architecture as Phi-4, but generates longer, more comprehensive outputs structured into a step-by-step reasoning trace and final answer.",match:{equals:"phi-4-reasoning-plus"},prices:{input_mtok:.07,output_mtok:.35}},{id:"phi-4-reasoning-plus:free",name:"Phi 4 Reasoning Plus (free)",description:"Phi-4-reasoning-plus is an enhanced 14B parameter model from Microsoft, fine-tuned from Phi-4 with additional reinforcement learning to boost accuracy on math, science, and code reasoning tasks. It uses the same dense decoder-only transformer architecture as Phi-4, but generates longer, more comprehensive outputs structured into a step-by-step reasoning trace and final answer.",match:{equals:"phi-4-reasoning-plus:free"},prices:{}},{id:"phi-4-reasoning:free",name:"Phi 4 Reasoning (free)",description:"Phi-4-reasoning is a 14B parameter dense decoder-only transformer developed by Microsoft, fine-tuned from Phi-4 to enhance complex reasoning capabilities. It uses a combination of supervised fine-tuning on chain-of-thought traces and reinforcement learning, targeting math, science, and code reasoning tasks. With a 32k context window and high inference efficiency, it is optimized for structured responses in a two-part format: reasoning trace followed by a final solution.",match:{equals:"phi-4-reasoning:free"},prices:{}},{id:"text-embedding-3-large",match:{equals:"text-embedding-3-large"},prices:{input_mtok:.13}},{id:"text-embedding-3-small",match:{equals:"text-embedding-3-small"},prices:{input_mtok:.02}},{id:"wizardlm-2-8x22b",name:"WizardLM-2 8x22B",description:"WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models.",match:{equals:"wizardlm-2-8x22b"},prices:{input_mtok:.48,output_mtok:.48}}]},{id:"cerebras",name:"Cerebras",pricing_urls:["https://www.cerebras.ai/pricing#pricing","https://inference-docs.cerebras.ai/models/openai-oss"],api_pattern:"https://api\\.cerebras\\.ai",model_match:{contains:"cerebras"},provider_match:{contains:"cerebras"},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"gpt-oss-120b",name:"GPT-OSS 120B",description:"OpenAI's flagship open source model, built on a Mixture-of-Experts (MoE) architecture with 120 billion parameters and 128 experts. Delivers frontier reasoning capabilities with record-breaking inference speeds on Cerebras hardware (~3,000 tokens/second).",match:{or:[{equals:"gpt-oss-120b"},{starts_with:"cerebras/gpt-oss-120b"},{starts_with:"cerebras:gpt-oss-120b"}]},context_window:131072,price_comments:"Developer tier pricing. Free tier: 65k context, Paid tier: 131k context.",prices:{input_mtok:.35,output_mtok:.75}},{id:"llama-3.3-70b",name:"Llama 3.3 70B",description:"Meta's enhanced 70B model delivering 405B-level accuracy. Optimized for chat, coding, instruction following, mathematics, and reasoning with high-speed inference on Cerebras hardware (~2,100 tokens/second).",match:{or:[{equals:"llama-3.3-70b"},{starts_with:"cerebras/llama-3.3-70b"},{starts_with:"cerebras:llama-3.3-70b"}]},context_window:128e3,price_comments:"Developer tier pricing. Free tier: 65k context, Paid tier: 128k context.",prices:{input_mtok:.85,output_mtok:1.2}},{id:"llama3.1-8b",name:"Llama 3.1 8B",description:"Meta's Llama 3.1 8B model for general-purpose tasks including chat, coding, and instruction following. Optimized for fast inference on Cerebras hardware (~2,200 tokens/second).",match:{or:[{equals:"llama3.1-8b"},{starts_with:"cerebras/llama3.1-8b"},{starts_with:"cerebras:llama3.1-8b"}]},context_window:32768,price_comments:"Developer tier pricing. Free tier: 8k context, Paid tier: 32k context.",prices:{input_mtok:.1,output_mtok:.1}},{id:"qwen-3-32b",name:"Qwen 3 32B",description:"Qwen's 32B parameter model with enhanced reasoning and coding capabilities. Supports both standard and reasoning modes for complex tasks, with fast inference speeds on Cerebras hardware (~2,600 tokens/second).",match:{or:[{equals:"qwen-3-32b"},{starts_with:"cerebras/qwen-3-32b"},{starts_with:"cerebras:qwen-3-32b"}]},context_window:131072,price_comments:"Developer tier pricing. Free tier: 65k context, Paid tier: 131k context.",prices:{input_mtok:.4,output_mtok:.8}},{id:"qwen-3-coder-480b",name:"qwen-3-coder-480b",match:{equals:"qwen-3-coder-480b"},price_comments:"Seems to be no longer available on cerebras, here to help with tests",prices:{}}]},{id:"cohere",name:"Cohere",pricing_urls:["https://cohere.com/pricing"],api_pattern:"https://api\\.cohere\\.ai",model_match:{starts_with:"command-"},provider_match:{contains:"cohere"},extractors:[{api_flavor:"default",root:["usage","billed_units"],model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:"output_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"embeddings",root:["meta","billed_units"],model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0}]}],models:[{id:"command",name:"Command",description:"Command is an instruction-following conversational model that performs language tasks with high quality, more reliably and with a longer context than our base generative models.",match:{equals:"command"},prices:{input_mtok:1,output_mtok:2}},{id:"command-a",name:"Command A",description:`Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases.
3
+ Compared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.`,match:{starts_with:"command-a"},prices:{input_mtok:2.5,output_mtok:10}},{id:"command-r",name:"Command R",description:"Command-R is a 35B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents.",match:{or:[{equals:"command-r"},{equals:"command-r-08-2024"}]},prices:{input_mtok:.15,output_mtok:.6}},{id:"command-r-plus",name:"Command R+",description:"Command R+ is a new, 104B-parameter LLM from Cohere. It's useful for roleplay, general consumer usecases, and Retrieval Augmented Generation (RAG).",match:{or:[{equals:"command-r-plus"},{equals:"command-r-plus-08-2024"}]},prices:{input_mtok:2.5,output_mtok:10}},{id:"command-r7b",name:"Command R7B",description:"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps.",match:{or:[{equals:"command-r7b"},{equals:"command-r7b-12-2024"}]},prices:{input_mtok:.0375,output_mtok:.15}},{id:"embed-v4.0",name:"Embed v4.0",description:"Embed v4.0 is a state-of-the-art embedding model designed for precise retrieval across noisy, multilingual, and multimodal data.",match:{equals:"embed-v4.0"},context_window:128e3,prices:{input_mtok:.12}}]},{id:"deepseek",name:"Deepseek",pricing_urls:["https://api-docs.deepseek.com/quick_start/pricing"],api_pattern:"https://api\\.deepseek\\.com",price_comments:'Deepseek off-peak pricing applies "UTC 16:30-00:30" so we switch it around and use the off-peak pricing as the default (first) price then the second price with a constraint is the "standard" pricing that applies "UTC 00:30-16:30".',model_match:{contains:"deepseek"},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"deepseek-chat",name:"DeepSeek Chat",description:"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.",match:{or:[{starts_with:"deepseek-chat"},{equals:"deepseek-chat-v3-0324"}]},context_window:64e3,prices:[{prices:{input_mtok:.135,cache_read_mtok:.035,output_mtok:.55}},{constraint:{start_time:"00:30:00Z",end_time:"16:30:00Z",type:"time_of_date"},prices:{input_mtok:.27,cache_read_mtok:.07,output_mtok:1.1}}]},{id:"deepseek-reasoner",name:"Deepseek R1",description:"DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.",match:{or:[{equals:"deepseek-reasoner"},{starts_with:"deepseek-r1"},{equals:"deepseek-r1-0528"}]},context_window:64e3,prices:[{prices:{input_mtok:.135,cache_read_mtok:.035,output_mtok:.55}},{constraint:{start_time:"00:30:00Z",end_time:"16:30:00Z",type:"time_of_date"},prices:{input_mtok:.55,cache_read_mtok:.14,output_mtok:2.19}}]},{id:"deepseek-v3.1-terminus",name:"DeepSeek V3.1 Terminus",description:"DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities.",match:{equals:"deepseek-v3.1-terminus"},prices:{input_mtok:.27,cache_read_mtok:.13,output_mtok:.95}},{id:"deepseek-v3.2",name:"DeepSeek V3.2",description:"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.",match:{equals:"deepseek-v3.2"},prices:{input_mtok:.2288,output_mtok:.3432}},{id:"deepseek-v3.2-exp",name:"DeepSeek V3.2 Exp",description:"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures.",match:{equals:"deepseek-v3.2-exp"},prices:{input_mtok:.27,output_mtok:.41}},{id:"deepseek-v4-flash",name:"DeepSeek V4 Flash",description:"DeepSeek-V4-Flash. Supports both non-thinking and thinking (default) modes, JSON output, tool calls, chat prefix completion, and FIM completion (non-thinking only).",match:{or:[{starts_with:"deepseek-v4-flash"}]},context_window:1e6,prices:{input_mtok:.14,cache_read_mtok:.0028,output_mtok:.28}},{id:"deepseek-v4-pro",name:"DeepSeek V4 Pro",description:"DeepSeek-V4-Pro. Supports both non-thinking and thinking (default) modes, JSON output, tool calls, chat prefix completion, and FIM completion (non-thinking only).",match:{or:[{starts_with:"deepseek-v4-pro"}]},context_window:1e6,prices:{input_mtok:.435,cache_read_mtok:.003625,output_mtok:.87}}]},{id:"doubleword",name:"Doubleword",pricing_urls:["https://docs.doubleword.ai/inference-api/models"],api_pattern:"https://api\\.doubleword\\.ai",price_comments:"Doubleword publishes Realtime, Async, and Batch prices. This provider currently encodes only Realtime pricing.",extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","cache_write_tokens"],dest:"cache_write_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"responses",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:["input_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"embeddings",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0}]}],models:[{id:"Qwen/Qwen3-14B-FP8",name:"Qwen3 14B",match:{equals:"Qwen/Qwen3-14B-FP8"},prices:{input_mtok:.05,output_mtok:.6}},{id:"Qwen/Qwen3-Embedding-8B",name:"Qwen3 Embedding 8B",match:{equals:"Qwen/Qwen3-Embedding-8B"},prices:{input_mtok:.04}},{id:"Qwen/Qwen3-VL-235B-A22B-Instruct-FP8",name:"Qwen3 VL 235B A22B Instruct",match:{equals:"Qwen/Qwen3-VL-235B-A22B-Instruct-FP8"},prices:{input_mtok:.6,output_mtok:1.2}},{id:"Qwen/Qwen3-VL-30B-A3B-Instruct-FP8",name:"Qwen3 VL 30B A3B Instruct",match:{equals:"Qwen/Qwen3-VL-30B-A3B-Instruct-FP8"},prices:{input_mtok:.16,output_mtok:.8}},{id:"Qwen/Qwen3.5-35B-A3B-FP8",name:"Qwen3.5 35B A3B",match:{equals:"Qwen/Qwen3.5-35B-A3B-FP8"},prices:{input_mtok:.25,output_mtok:2}},{id:"Qwen/Qwen3.5-397B-A17B",name:"Qwen3.5 397B A17B",match:{equals:"Qwen/Qwen3.5-397B-A17B"},prices:{input_mtok:.6,output_mtok:3.6}},{id:"Qwen/Qwen3.5-9B",name:"Qwen3.5 9B",match:{equals:"Qwen/Qwen3.5-9B"},prices:{input_mtok:.08,output_mtok:.7}},{id:"Qwen/Qwen3.6-35B-A3B-FP8",name:"Qwen3.6 35B A3B",match:{equals:"Qwen/Qwen3.6-35B-A3B-FP8"},prices:{input_mtok:.25,output_mtok:2}},{id:"deepseek-ai/DeepSeek-V4-Flash",name:"DeepSeek V4 Flash",match:{equals:"deepseek-ai/DeepSeek-V4-Flash"},prices:{input_mtok:.14,output_mtok:.28}},{id:"deepseek-ai/DeepSeek-V4-Pro",name:"DeepSeek V4 Pro",match:{equals:"deepseek-ai/DeepSeek-V4-Pro"},prices:{input_mtok:1.74,output_mtok:3.48}},{id:"google/gemma-4-31B-it",name:"Gemma 4 31B IT",match:{equals:"google/gemma-4-31B-it"},prices:{input_mtok:.14,output_mtok:.4}},{id:"mistralai/Devstral-2-123B-Instruct-2512",name:"Devstral 2 123B Instruct 2512",match:{equals:"mistralai/Devstral-2-123B-Instruct-2512"},prices:{input_mtok:.4,output_mtok:2}},{id:"moonshotai/Kimi-K2.6",name:"Kimi K2.6",match:{equals:"moonshotai/Kimi-K2.6"},prices:{input_mtok:.95,output_mtok:4}},{id:"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4",name:"Nemotron 3 Super 120B A12B",match:{equals:"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4"},prices:{input_mtok:.3,output_mtok:.75}},{id:"openai/gpt-oss-20b",name:"GPT OSS 20B",match:{equals:"openai/gpt-oss-20b"},prices:{input_mtok:.04,output_mtok:.3}},{id:"zai-org/GLM-5.1-FP8",name:"GLM 5.1",match:{equals:"zai-org/GLM-5.1-FP8"},prices:{input_mtok:1.4,output_mtok:4.4}}]},{id:"fireworks",name:"Fireworks",pricing_urls:["https://fireworks.ai/pricing"],api_pattern:"https://api\\.fireworks\\.ai",model_match:{starts_with:"accounts/fireworks/models/"},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"deepseek-r1-0528",name:"DeepSeek R1 0528",description:"The updated DeepSeek-R1-0528 model delivers major improvements in reasoning, inference, and accuracy through enhanced post-training optimization and greater computational resources. It now performs at a level approaching top-tier models like O3 and Gemini 2.5 Pro, with notable gains in complex tasks such as math and programming.",match:{equals:"accounts/fireworks/models/deepseek-r1-0528"},context_window:16e4,prices:{input_mtok:3,output_mtok:8}},{id:"deepseek-v3-0324",name:"Deepseek V3 03-24",description:"A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token from Deepseek. Updated checkpoint.",match:{equals:"accounts/fireworks/models/deepseek-v3-0324"},context_window:16e4,price_comments:`docs give just one price - "Pricing Per 1M Tokens", we assume that's input and output`,prices:{input_mtok:.9,output_mtok:.9}},{id:"deepseek-v3p2",name:"Deepseek V3.2",description:"Model from Deepseek that harmonizes high computational efficiency with superior reasoning and agent performance. 675B parameter MoE model.",match:{equals:"accounts/fireworks/models/deepseek-v3p2"},context_window:163840,prices:{input_mtok:.56,cache_read_mtok:.28,output_mtok:1.68}},{id:"deepseek-v4-flash",name:"DeepSeek-V4-Flash",match:{equals:"accounts/fireworks/models/deepseek-v4-flash"},prices:{input_mtok:.14,cache_read_mtok:.028,output_mtok:.28}},{id:"deepseek-v4-pro",name:"DeepSeek-V4-Pro",match:{equals:"accounts/fireworks/models/deepseek-v4-pro"},prices:{input_mtok:1.74,cache_read_mtok:.145,output_mtok:3.48}},{id:"gemma-3-27b-it",name:"Gemma 3 27B Instruct",match:{equals:"accounts/fireworks/models/gemma-3-27b-it"},context_window:131e3,price_comments:`docs give just one price - "Pricing Per 1M Tokens", we assume that's input and output`,prices:{input_mtok:.1,output_mtok:.1}},{id:"glm-4p7",name:"GLM-4.7",description:"Next-generation general-purpose model from Z.ai optimized for coding, reasoning, and agentic workflows. 352B parameter MoE model with advanced thinking controls.",match:{equals:"accounts/fireworks/models/glm-4p7"},context_window:202752,prices:{input_mtok:.6,output_mtok:2.2}},{id:"glm-5p1",name:"GLM-5.1",match:{equals:"accounts/fireworks/models/glm-5p1"},prices:{input_mtok:1.4,cache_read_mtok:.26,output_mtok:4.4}},{id:"gpt-oss-120b",name:"OpenAI gpt-oss-120b",description:"OpenAI's open-weight 117B parameter MoE model designed for production, general purpose, high reasoning use-cases. Features powerful reasoning, agentic tasks, and versatile developer use cases.",match:{equals:"accounts/fireworks/models/gpt-oss-120b"},context_window:131072,prices:{input_mtok:.15,cache_read_mtok:.07,output_mtok:.6}},{id:"gpt-oss-20b",name:"OpenAI gpt-oss-20b",description:"OpenAI's open-weight 21.5B parameter model designed for powerful reasoning, agentic tasks, and versatile developer use cases. Optimized for lower latency and local or specialized tasks.",match:{equals:"accounts/fireworks/models/gpt-oss-20b"},context_window:131072,prices:{input_mtok:.07,cache_read_mtok:.04,output_mtok:.3}},{id:"kimi-k2p5",name:"Kimi K2.5",description:"Moonshot AI's flagship agentic model. Unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model. 1T parameter MoE model.",match:{equals:"accounts/fireworks/models/kimi-k2p5"},context_window:262144,prices:{input_mtok:.6,cache_read_mtok:.1,output_mtok:3}},{id:"kimi-k2p6",name:"Kimi K2.6",match:{equals:"accounts/fireworks/models/kimi-k2p6"},prices:{input_mtok:.95,cache_read_mtok:.16,output_mtok:4}},{id:"llama-v3p1-8b-instruct",name:"Llama 3.1 8B Instruct",description:"The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes. The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.",match:{equals:"accounts/fireworks/models/llama-v3p1-8b-instruct"},context_window:131e3,price_comments:`docs give just one price - "Pricing Per 1M Tokens", we assume that's input and output`,prices:{input_mtok:.2,output_mtok:.2}},{id:"llama4-maverick-instruct-basic",name:"Llama 4 Maverick Instruct (Basic)",description:"The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes. The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.",match:{equals:"accounts/fireworks/models/llama4-maverick-instruct-basic"},context_window:1e6,prices:{input_mtok:.22,output_mtok:.88}},{id:"minimax-m2p1",name:"MiniMax-M2.1",description:"Built for strong real-world performance across complex, multi-language, and agent-driven workflows. 228B parameter model with robust support for systems, backend, web, mobile, and office-style tasks.",match:{equals:"accounts/fireworks/models/minimax-m2p1"},context_window:204800,prices:{input_mtok:.3,output_mtok:1.2}},{id:"minimax-m2p7",name:"MiniMax M2.7",match:{equals:"accounts/fireworks/models/minimax-m2p7"},prices:{input_mtok:.3,cache_read_mtok:.06,output_mtok:1.2}},{id:"minimax-m3",name:"MiniMax M3",description:"Multimodal foundation model from MiniMax with text, image, and video inputs, a long context window, and long-horizon agentic work.",match:{equals:"accounts/fireworks/models/minimax-m3"},context_window:524288,prices:{input_mtok:.3,cache_read_mtok:.06,output_mtok:1.2}},{id:"qwen2p5-vl-72b-instruct",name:"Qwen2.5-VL 72B Instruct",description:"Latest Qwen's VLM model",match:{equals:"accounts/fireworks/models/qwen2p5-vl-72b-instruct"},context_window:128e3,price_comments:`docs give just one price - "Pricing Per 1M Tokens", we assume that's input and output`,prices:{input_mtok:.9,output_mtok:.9}},{id:"qwen3-235b-a22b",name:"Qwen3 235B-A22B",description:'Qwen3 is the latest evolution in the Qwen LLM series, featuring both dense and MoE models with major advancements in reasoning, agent capabilities, multilingual support, and instruction following. It uniquely allows seamless switching between "thinking" (for complex logic, math, coding) and "non-thinking" modes (for fast, general dialogue), delivering strong performance across tasks.',match:{equals:"accounts/fireworks/models/qwen3-235b-a22b"},context_window:128e3,prices:{input_mtok:.22,output_mtok:.88}},{id:"qwen3p6-plus",name:"Qwen3.6 Plus",match:{equals:"accounts/fireworks/models/qwen3p6-plus"},prices:{input_mtok:.5,cache_read_mtok:.1,output_mtok:3}}]},{id:"google",name:"Google",pricing_urls:["https://ai.google.dev/gemini-api/docs/pricing","https://cloud.google.com/vertex-ai/generative-ai/pricing"],api_pattern:"https://(.*\\.)?googleapis\\.com",model_match:{contains:"gemini"},provider_match:{or:[{contains:"google"},{contains:"vertex"},{contains:"gemini"}]},extractors:[{api_flavor:"default",root:"usageMetadata",model_path:"modelVersion",mappings:[{path:"promptTokenCount",dest:"input_tokens",required:!1},{path:"cachedContentTokenCount",dest:"cache_read_tokens",required:!1},{path:["cacheTokensDetails",{type:"array-match",field:"modality",match:{equals:"AUDIO"}},"tokenCount"],dest:"cache_audio_read_tokens",required:!1},{path:["promptTokensDetails",{type:"array-match",field:"modality",match:{equals:"AUDIO"}},"tokenCount"],dest:"input_audio_tokens",required:!1},{path:["candidatesTokensDetails",{type:"array-match",field:"modality",match:{equals:"AUDIO"}},"tokenCount"],dest:"output_audio_tokens",required:!1},{path:"candidatesTokenCount",dest:"output_tokens",required:!1},{path:"thoughtsTokenCount",dest:"output_tokens",required:!1},{path:"toolUsePromptTokenCount",dest:"input_tokens",required:!1}]},{api_flavor:"anthropic",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:"cache_creation_input_tokens",dest:"input_tokens",required:!1},{path:"cache_read_input_tokens",dest:"input_tokens",required:!1},{path:"cache_creation_input_tokens",dest:"cache_write_tokens",required:!1},{path:"cache_read_input_tokens",dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],fallback_model_providers:["anthropic"],models:[{id:"claude-3-5-haiku",match:{contains:"claude-3-5-haiku"},context_window:2e5,prices:{input_mtok:.8,cache_write_mtok:1,cache_read_mtok:.08,output_mtok:4}},{id:"claude-3-5-sonnet",match:{contains:"claude-3-5-sonnet"},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-3-7-sonnet",match:{contains:"claude-3-7-sonnet"},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-3-haiku",match:{contains:"claude-3-haiku"},context_window:2e5,prices:{input_mtok:.25,cache_write_mtok:.3,cache_read_mtok:.03,output_mtok:1.25}},{id:"claude-3-opus",match:{contains:"claude-3-opus"},prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"claude-4-opus",match:{or:[{contains:"claude-4-opus"},{contains:"claude-opus-4@"},{contains:"claude-opus-4-0"},{contains:"claude-opus-4-1"},{equals:"claude-opus-4"}]},context_window:2e5,prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"claude-4-sonnet",match:{or:[{contains:"claude-4-sonnet"},{contains:"claude-sonnet-4"}]},context_window:2e5,prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-fable-5",match:{contains:"claude-fable-5"},context_window:1e6,price_comments:"Flat pricing across full 1M context window. Ref: https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models",prices:{input_mtok:10,cache_write_mtok:12.5,cache_read_mtok:1,output_mtok:50}},{id:"claude-opus-4-6",match:{or:[{contains:"claude-4-6-opus"},{contains:"claude-opus-4-6"},{contains:"claude-4.6-opus"},{contains:"claude-opus-4.6"}]},context_window:2e5,prices:{input_mtok:{base:5,tiers:[{start:2e5,price:10}]},cache_write_mtok:{base:6.25,tiers:[{start:2e5,price:12.5}]},cache_read_mtok:{base:.5,tiers:[{start:2e5,price:1}]},output_mtok:{base:25,tiers:[{start:2e5,price:37.5}]}}},{id:"claude-opus-4-7",match:{or:[{contains:"claude-4-7-opus"},{contains:"claude-opus-4-7"},{contains:"claude-4.7-opus"},{contains:"claude-opus-4.7"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window. Ref: https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"claude-opus-4-8",match:{or:[{contains:"claude-4-8-opus"},{contains:"claude-opus-4-8"},{contains:"claude-4.8-opus"},{contains:"claude-opus-4.8"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window. Ref: https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"gemini-1.0-pro-vision-001",name:"gemini 1.0 pro vision",description:"Google's first-generation advanced multimodal model that can understand text, code, and images. It provides strong reasoning capabilities and follows instructions effectively.",match:{equals:"gemini-1.0-pro-vision-001"},context_window:32768,price_comments:"I can't find anything about this model or it's pricing, so trusting the original source",prices:{input_mtok:.125,output_mtok:.375}},{id:"gemini-1.5-flash",name:"gemini 1.5 flash",description:"A faster, more cost-effective variant of Gemini 1.5 that maintains strong capabilities while optimizing for performance and cost efficiency. Suitable for production deployments requiring high throughput.",match:{contains:"gemini-1.5-flash"},context_window:1e6,prices:{input_mtok:{base:.075,tiers:[{start:128e3,price:.15}]},cache_read_mtok:{base:.01875,tiers:[{start:128e3,price:.0375}]},output_mtok:{base:.3,tiers:[{start:128e3,price:.6}]}}},{id:"gemini-1.5-pro",name:"gemini 1.5 Pro",description:"Google's most capable multimodal model with an extremely long context window of up to 1 million tokens. It excels at complex reasoning, long-form content processing, and multimodal understanding.",match:{contains:"gemini-1.5-pro"},context_window:1e6,prices:{input_mtok:{base:1.25,tiers:[{start:128e3,price:2.5}]},output_mtok:{base:5,tiers:[{start:128e3,price:10}]}}},{id:"gemini-2.0-flash",name:"gemini 2.0 flash",description:"The newest generation of Google's Gemini models, featuring improved reasoning, instruction following, and factual accuracy, with the Flash variant optimized for cost-efficiency and performance.",match:{or:[{ends_with:"gemini-2.0-flash"},{contains:"gemini-2.0-flash-0"},{contains:"gemini-2.0-flash-exp"},{contains:"gemini-2.0-flash-thinking"},{contains:"gemini-2.0-flash-latest"}]},context_window:1e6,prices:{input_mtok:.1,cache_read_mtok:.025,output_mtok:.4,input_audio_mtok:.7,cache_audio_read_mtok:.175}},{id:"gemini-2.0-flash-lite",name:"gemini 2.0 flash lite",description:"A lighter, more cost-effective version of Gemini 2.0 Flash, designed for applications requiring high efficiency while maintaining good performance. Ideal for high-volume, cost-sensitive deployments.",match:{contains:"gemini-2.0-flash-lite"},context_window:1e6,prices:{input_mtok:.075,output_mtok:.3}},{id:"gemini-2.5-flash",name:"Gemini 2.5 Flash",description:`Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.`,match:{or:[{equals:"gemini-2.5-flash"},{equals:"gemini-2.5-flash-latest"},{equals:"gemini-2.5-flash-preview-09-2025"}]},prices:{input_mtok:.3,cache_read_mtok:.03,output_mtok:2.5,input_audio_mtok:1,cache_audio_read_mtok:.1}},{id:"gemini-2.5-flash-image",name:"Gemini 2.5 Flash Image",description:"Google's specialized image generation model optimized for fast, high-quality image generation. Outputs images at 1024x1024 resolution, with each image consuming 1290 output tokens.",match:{or:[{equals:"gemini-2.5-flash-image"},{equals:"gemini-2.5-flash-image-preview"}]},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image. Image output is priced at $30 per 1M tokens, with each 1024x1024 image = 1290 tokens = $0.039/image. Cache pricing is not available for this model.",prices:{input_mtok:.3,output_mtok:30}},{id:"gemini-2.5-flash-lite",name:"Gemini 2.5 Flash Lite",description:'Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.',match:{or:[{equals:"gemini-2.5-flash-lite"},{starts_with:"gemini-2.5-flash-lite-preview"}]},context_window:1e6,prices:{input_mtok:.1,cache_read_mtok:.01,output_mtok:.4,input_audio_mtok:.3,cache_audio_read_mtok:.03}},{id:"gemini-2.5-flash-preview",name:"Gemini 2.5 Flash Preview 05-20",description:`Gemini 2.5 Flash May 20th Checkpoint is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.`,match:{or:[{contains:"gemini-2.5-flash-preview-05-20"},{contains:"gemini-2.5-flash-preview-04-17"},{equals:"gemini-2.5-flash-preview-05-20:thinking"},{equals:"gemini-2.5-flash-preview"},{equals:"gemini-2.5-flash-preview:thinking"}]},price_comments:"from https://cloud.google.com/vertex-ai/generative-ai/pricing should be retired 2025-07-15",prices:{input_mtok:.15,output_mtok:.6},deprecated:!0},{id:"gemini-2.5-pro",name:"Gemini 2.5 Pro",description:`Gemini 2.5 Pro is Google's state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs "thinking" capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.`,match:{starts_with:"gemini-2.5-pro"},price_comments:"See https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro",prices:{input_mtok:{base:1.25,tiers:[{start:2e5,price:2.5}]},cache_read_mtok:{base:.125,tiers:[{start:2e5,price:.25}]},output_mtok:{base:10,tiers:[{start:2e5,price:15}]}}},{id:"gemini-3-flash-preview",name:"Gemini 3 Flash Preview",description:"Google's ultra-fast frontier model optimized for speed and efficiency. Delivers state-of-the-art performance while maintaining low latency and cost, with improved reasoning and coding capabilities.",match:{or:[{equals:"gemini-3-flash-preview"},{starts_with:"gemini-3-flash-preview-"}]},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing. Standard pricing shown; Batch API offers 50% discount on input/output.",prices:{input_mtok:.5,cache_read_mtok:.05,output_mtok:3,input_audio_mtok:1,cache_audio_read_mtok:.1}},{id:"gemini-3-pro-image-preview",name:"Gemini 3 Pro Image Preview",description:"Google's image generation model optimized for high-quality image generation. Supports 1K/2K and 4K resolution outputs with flexible pricing based on image dimensions.",match:{or:[{starts_with:"gemini-3-pro-image-preview"},{equals:"gemini-3-pro-image-preview"}]},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image. Image output is priced at $120 per 1M tokens, with each 1K/2K image = 1120 tokens = $0.134/image and each 4K image = 2000 tokens = $0.24/image.",prices:{input_mtok:2,output_mtok:120}},{id:"gemini-3-pro-preview",name:"Gemini 3 Pro Preview",description:"The best model in the world for multimodal understanding, and our most powerful agentic and vibe-coding model yet.",match:{or:[{starts_with:"gemini-3-pro-preview"},{equals:"gemini-3-pro-text-preview"}]},prices:{input_mtok:{base:2,tiers:[{start:2e5,price:4}]},cache_read_mtok:{base:.2,tiers:[{start:2e5,price:.4}]},output_mtok:{base:12,tiers:[{start:2e5,price:18}]}}},{id:"gemini-3.1-flash-image-preview",name:"Gemini 3.1 Flash Image Preview",description:"Google's latest image generation model (Nano Banana 2) optimized for fast, high-quality image generation. Supports multiple output resolutions from 512px to 4K, with text and thinking output priced separately from image output tokens.",match:{starts_with:"gemini-3.1-flash-image-preview"},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing. Image output is priced at $60 per 1M tokens. Preview model - pricing may change.",prices:{input_mtok:.5,output_mtok:60}},{id:"gemini-3.1-flash-lite",name:"Gemini 3.1 Flash Lite",description:"Google's fastest and most cost-efficient Gemini 3 series model, built for intelligence at scale. Optimized for high-volume, low-latency applications while maintaining strong multimodal capabilities.",match:{starts_with:"gemini-3.1-flash-lite"},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing.",prices:{input_mtok:.25,cache_read_mtok:.025,output_mtok:1.5,input_audio_mtok:.5,cache_audio_read_mtok:.05}},{id:"gemini-3.1-pro-preview",name:"Gemini 3.1 Pro Preview",description:"The latest performance, intelligence, and usability improvements to the best model family in the world for multimodal understanding, agentic capabilities, and vibe-coding.",match:{starts_with:"gemini-3.1-pro-preview"},prices:{input_mtok:{base:2,tiers:[{start:2e5,price:4}]},cache_read_mtok:{base:.2,tiers:[{start:2e5,price:.4}]},output_mtok:{base:12,tiers:[{start:2e5,price:18}]}}},{id:"gemini-3.5-flash",name:"Gemini 3.5 Flash",description:"Google's most intelligent model built for speed, combining frontier intelligence with improved reasoning, coding, and multimodal understanding.",match:{starts_with:"gemini-3.5-flash"},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing. Standard tier pricing shown; Batch and Flex tiers offer 50% discount on input/output.",prices:{input_mtok:1.5,cache_read_mtok:.15,output_mtok:9}},{id:"gemini-embedding-001",match:{equals:"gemini-embedding-001"},prices:{input_mtok:.15}},{id:"gemini-flash-1.5",name:"Gemini 1.5 Flash",description:"Gemini 1.5 Flash is a foundation model that performs well at a variety of multimodal tasks such as visual understanding, classification, summarization, and creating content from image, audio and video. It's adept at processing visual and text inputs such as photographs, documents, infographics, and screenshots.",match:{equals:"gemini-flash-1.5"},price_comments:"See https://ai.google.dev/gemini-api/docs/pricing#gemini-1.5-flash",prices:{input_mtok:{base:.075,tiers:[{start:128e3,price:.15}]},cache_read_mtok:{base:.01875,tiers:[{start:128e3,price:.0375}]},output_mtok:{base:.3,tiers:[{start:128e3,price:.6}]}}},{id:"gemini-flash-1.5-8b",name:"gemini 1.5 flash",description:"A faster, more cost-effective variant of Gemini 1.5 that maintains strong capabilities while optimizing for performance and cost efficiency. Suitable for production deployments requiring high throughput.",match:{equals:"gemini-flash-1.5-8b"},context_window:1e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing#gemini-1.5-flash-8b",prices:{input_mtok:{base:.0375,tiers:[{start:128e3,price:.075}]},cache_read_mtok:{base:.01,tiers:[{start:128e3,price:.02}]},output_mtok:{base:.15,tiers:[{start:128e3,price:.3}]}}},{id:"gemini-live-2.5-flash-preview",match:{or:[{starts_with:"gemini-live-2.5-flash-preview"},{starts_with:"gemini-2.5-flash-native-audio-preview"}]},prices:{input_mtok:.5,output_mtok:2,input_audio_mtok:3,output_audio_mtok:12}},{id:"gemini-pro",name:"gemini 1.0 pro",description:"Google's first-generation advanced multimodal model that can understand text, code, and images. It provides strong reasoning capabilities and follows instructions effectively.",match:{or:[{equals:"gemini-pro"},{equals:"gemini-1.0-pro"}]},context_window:32768,price_comments:"I can't find anything so trusting these prices, not sure the model still exists",prices:{input_mtok:.125,output_mtok:.375}},{id:"gemini-pro-1.5",name:"Gemini 1.5 Pro",description:"Google's latest multimodal model, supports image and video[0] in text or chat prompts.",match:{equals:"gemini-pro-1.5"},context_window:2e6,price_comments:"See https://ai.google.dev/gemini-api/docs/pricing#gemini-1.5-pro",prices:{input_mtok:{base:1.25,tiers:[{start:128e3,price:2.5}]},cache_read_mtok:{base:.3125,tiers:[{start:128e3,price:.625}]},output_mtok:{base:5,tiers:[{start:128e3,price:10}]}}},{id:"gemma-2-27b-it",name:"Gemma 2 27B",description:"Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models. Gemma models are well-suited for a variety of text generation and instruction-following tasks.",match:{equals:"gemma-2-27b-it"},price_comments:"Imported from OpenRouter pricing; verify against Google pricing when native API pricing is published.",prices:{input_mtok:.65,output_mtok:.65}},{id:"gemma-3",name:"Gemma 3 (free)",description:"Lightweight, state-of the art, open model built from the same technology that powers our Gemini models.",match:{or:[{starts_with:"gemma-3-"},{equals:"gemma-3"}]},prices:{}},{id:"gemma-3n",name:"Gemma 3n (free)",description:"Our open model built for efficient performance on everyday devices like mobile phones, laptops, and tablets.",match:{or:[{starts_with:"gemma-3n"}]},prices:{}},{id:"gemma-4-26b-a4b-it",name:"Gemma 4 26B A4B",description:"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference.",match:{equals:"gemma-4-26b-a4b-it"},price_comments:"Imported from OpenRouter pricing; verify against Google pricing when native API pricing is published.",prices:{input_mtok:.06,output_mtok:.33}},{id:"gemma-4-31b-it",name:"Gemma 4 31B",description:"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. It features a 256K token context window, configurable thinking/reasoning mode, and native function calling.",match:{equals:"gemma-4-31b-it"},price_comments:"Imported from OpenRouter pricing; verify against Google pricing when native API pricing is published.",prices:{input_mtok:.12,cache_read_mtok:.09,output_mtok:.36}}]},{id:"groq",name:"Groq",pricing_urls:["https://groq.com/pricing/"],api_pattern:"https://api\\.groq\\.com",extractors:[{api_flavor:"default",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"deepseek-r1-distill-llama-70b",name:"DeepSeek R1 Distill Llama 70B",match:{equals:"deepseek-r1-distill-llama-70b"},context_window:131072,prices:{input_mtok:.75,output_mtok:.99}},{id:"gemma-7b-it",match:{equals:"gemma-7b-it"},prices:{input_mtok:.07,output_mtok:.07}},{id:"gemma2-9b-it",name:"Gemma 2 9B 8k",match:{or:[{equals:"gemma2-9b-it"},{equals:"gemma2-9b"}]},prices:{input_mtok:.2,output_mtok:.2}},{id:"llama-3.1-405b-reasoning",match:{equals:"llama-3.1-405b-reasoning"},prices:{input_mtok:.59,output_mtok:.79}},{id:"llama-3.1-70b-versatile",match:{equals:"llama-3.1-70b-versatile"},prices:{input_mtok:.59,output_mtok:.79}},{id:"llama-3.1-8b-instant",name:"Llama 3.1 8B Instant 128k",match:{equals:"llama-3.1-8b-instant"},prices:{input_mtok:.05,output_mtok:.08}},{id:"llama-3.2-11b-text-preview",match:{equals:"llama-3.2-11b-text-preview"},prices:{input_mtok:.18,output_mtok:.18}},{id:"llama-3.2-11b-vision-preview",match:{equals:"llama-3.2-11b-vision-preview"},prices:{input_mtok:.18,output_mtok:.18}},{id:"llama-3.2-1b-preview",match:{equals:"llama-3.2-1b-preview"},prices:{input_mtok:.04,output_mtok:.04}},{id:"llama-3.2-3b-preview",match:{equals:"llama-3.2-3b-preview"},prices:{input_mtok:.06,output_mtok:.06}},{id:"llama-3.2-90b-text-preview",match:{equals:"llama-3.2-90b-text-preview"},prices:{input_mtok:.9,output_mtok:.9}},{id:"llama-3.2-90b-vision-preview",match:{equals:"llama-3.2-90b-vision-preview"},prices:{input_mtok:.9,output_mtok:.9}},{id:"llama-3.3-70b-specdec",match:{equals:"llama-3.3-70b-specdec"},prices:{input_mtok:.59,output_mtok:.99}},{id:"llama-3.3-70b-versatile",name:"Llama 3.3 70B Versatile 128k",match:{equals:"llama-3.3-70b-versatile"},prices:{input_mtok:.59,output_mtok:.79}},{id:"llama-guard-3-8b",match:{equals:"llama-guard-3-8b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"llama2-70b-4096",match:{equals:"llama2-70b-4096"},prices:{input_mtok:.7,output_mtok:.8}},{id:"llama3-70b-8192",match:{equals:"llama3-70b-8192"},prices:{input_mtok:.59,output_mtok:.79}},{id:"llama3-8b-8192",match:{equals:"llama3-8b-8192"},prices:{input_mtok:.05,output_mtok:.08}},{id:"llama3-groq-70b-8192-tool-use-preview",match:{equals:"llama3-groq-70b-8192-tool-use-preview"},prices:{input_mtok:.89,output_mtok:.89}},{id:"llama3-groq-8b-8192-tool-use-preview",match:{equals:"llama3-groq-8b-8192-tool-use-preview"},prices:{input_mtok:.19,output_mtok:.19}},{id:"meta-llama/llama-4-maverick-17b-128e-instruct",name:"Llama 4 Maverick 17B 128E",match:{equals:"meta-llama/llama-4-maverick-17b-128e-instruct"},context_window:131072,prices:{input_mtok:.2,output_mtok:.6}},{id:"meta-llama/llama-4-scout-17b-16e-instruct",name:"Llama 4 Scout (17Bx16E) 128k",match:{equals:"meta-llama/llama-4-scout-17b-16e-instruct"},prices:{input_mtok:.11,output_mtok:.34}},{id:"meta-llama/llama-guard-4-12b",name:"Llama Guard 4 12B",match:{equals:"meta-llama/llama-guard-4-12b"},context_window:131072,prices:{input_mtok:.2,output_mtok:.2}},{id:"mistral-saba-24b",match:{equals:"mistral-saba-24b"},prices:{input_mtok:.79,output_mtok:.79}},{id:"mixtral-8x7b-32768",match:{equals:"mixtral-8x7b-32768"},prices:{input_mtok:.24,output_mtok:.24}},{id:"moonshotai/kimi-k2-instruct",name:"Kimi K2 1T 128k",match:{or:[{equals:"moonshotai/kimi-k2-instruct"},{equals:"moonshotai/kimi-k2-instruct-0905"}]},context_window:131072,prices:{input_mtok:1,cache_read_mtok:.5,output_mtok:3}},{id:"openai/gpt-oss-120b",description:`GPT-OSS 120B is OpenAI's flagship open source model, built on a Mixture-of-Experts (MoE) architecture with
4
4
  120 billion parameters and 128 experts.
5
5
  `,match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-safeguard-20b"}]},context_window:131072,prices:{input_mtok:.15,cache_read_mtok:.075,output_mtok:.6}},{id:"openai/gpt-oss-20b",description:`GPT-OSS 20B is OpenAI's flagship open source model, built on a Mixture-of-Experts (MoE) architecture with
6
6
  20 billion parameters and 32 experts.
7
- `,match:{equals:"openai/gpt-oss-20b"},context_window:131072,prices:{input_mtok:.075,cache_read_mtok:.0375,output_mtok:.3}},{id:"qwen/qwen3-32b",name:"Qwen3 32B 131k",match:{equals:"qwen/qwen3-32b"},prices:{input_mtok:.29,output_mtok:.59}}]},{id:"huggingface_cerebras",name:"HuggingFace (cerebras)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/cerebras",provider_match:{and:[{contains:"huggingface"},{contains:"cerebras"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"meta-llama/Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-fast"}]},prices:{input_mtok:.1,output_mtok:.1}}]},{id:"huggingface_fireworks-ai",name:"HuggingFace (fireworks-ai)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/fireworks-ai",provider_match:{and:[{contains:"huggingface"},{contains:"fireworks-ai"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.9,output_mtok:.9}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:.6}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.05,output_mtok:.2}}]},{id:"huggingface_groq",name:"HuggingFace (groq)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/groq",provider_match:{and:[{contains:"huggingface"},{contains:"groq"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"Qwen/Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"qwen/qwen3-32b"},{equals:"qwen/qwen3-32b-fast"}]},context_window:131072,prices:{input_mtok:.29,output_mtok:.59}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.59,output_mtok:.79}},{id:"meta-llama/Llama-4-Scout-17B-16E-Instruct",name:"Llama-4-Scout-17B-16E-Instruct",match:{or:[{equals:"meta-llama/llama-4-scout-17b-16e-instruct"},{equals:"meta-llama/llama-4-scout-17b-16e-instruct-fast"}]},context_window:131072,prices:{input_mtok:.11,output_mtok:.34}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:.75}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.1,output_mtok:.5}}]},{id:"huggingface_hyperbolic",name:"HuggingFace (hyperbolic)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/hyperbolic",provider_match:{and:[{contains:"huggingface"},{contains:"hyperbolic"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"Qwen/Qwen2.5-VL-72B-Instruct",name:"Qwen2.5-VL-72B-Instruct",match:{or:[{equals:"qwen/qwen2.5-vl-72b-instruct"},{equals:"qwen/qwen2.5-vl-72b-instruct-fast"}]},context_window:32768,prices:{input_mtok:.6,output_mtok:.6}},{id:"Qwen/Qwen2.5-VL-7B-Instruct",name:"Qwen2.5-VL-7B-Instruct",match:{or:[{equals:"qwen/qwen2.5-vl-7b-instruct"},{equals:"qwen/qwen2.5-vl-7b-instruct-fast"}]},context_window:32768,prices:{input_mtok:.2,output_mtok:.2}},{id:"Qwen/Qwen3-235B-A22B-Instruct-2507",name:"Qwen3-235B-A22B-Instruct-2507",match:{or:[{equals:"qwen/qwen3-235b-a22b-instruct-2507"},{equals:"qwen/qwen3-235b-a22b-instruct-2507-fast"}]},context_window:262144,prices:{input_mtok:2,output_mtok:2}},{id:"Qwen/Qwen3-Coder-480B-A35B-Instruct",name:"Qwen3-Coder-480B-A35B-Instruct",match:{or:[{equals:"qwen/qwen3-coder-480b-a35b-instruct"},{equals:"qwen/qwen3-coder-480b-a35b-instruct-fast"}]},context_window:262144,prices:{input_mtok:2,output_mtok:2}},{id:"Qwen/Qwen3-Next-80B-A3B-Instruct",name:"Qwen3-Next-80B-A3B-Instruct",match:{or:[{equals:"qwen/qwen3-next-80b-a3b-instruct"},{equals:"qwen/qwen3-next-80b-a3b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.3,output_mtok:.3}},{id:"Qwen/Qwen3-Next-80B-A3B-Thinking",name:"Qwen3-Next-80B-A3B-Thinking",match:{or:[{equals:"qwen/qwen3-next-80b-a3b-thinking"},{equals:"qwen/qwen3-next-80b-a3b-thinking-fast"}]},context_window:262144,prices:{input_mtok:.3,output_mtok:.3}},{id:"deepseek-ai/DeepSeek-R1",name:"DeepSeek-R1",match:{or:[{equals:"deepseek-ai/deepseek-r1"},{equals:"deepseek-ai/deepseek-r1-fast"}]},context_window:163840,prices:{input_mtok:2,output_mtok:2}},{id:"deepseek-ai/DeepSeek-R1-0528",name:"DeepSeek-R1-0528",match:{or:[{equals:"deepseek-ai/deepseek-r1-0528"},{equals:"deepseek-ai/deepseek-r1-0528-fast"}]},context_window:163840,prices:{input_mtok:3,output_mtok:3}},{id:"deepseek-ai/DeepSeek-V3-0324",name:"DeepSeek-V3-0324",match:{or:[{equals:"deepseek-ai/deepseek-v3-0324"},{equals:"deepseek-ai/deepseek-v3-0324-fast"}]},context_window:163840,prices:{input_mtok:1.25,output_mtok:1.25}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.4,output_mtok:.4}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.3,output_mtok:.3}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.1,output_mtok:.1}}]},{id:"huggingface_nebius",name:"HuggingFace (nebius)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/nebius",provider_match:{and:[{contains:"huggingface"},{contains:"nebius"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"NousResearch/Hermes-4-405B",name:"Hermes-4-405B",match:{or:[{equals:"nousresearch/hermes-4-405b"},{equals:"nousresearch/hermes-4-405b-fast"}]},context_window:131072,prices:{input_mtok:1,output_mtok:3}},{id:"NousResearch/Hermes-4-70B",name:"Hermes-4-70B",match:{or:[{equals:"nousresearch/hermes-4-70b"},{equals:"nousresearch/hermes-4-70b-fast"}]},context_window:131072,prices:{input_mtok:.13,output_mtok:.4}},{id:"PrimeIntellect/INTELLECT-3-FP8",name:"INTELLECT-3-FP8",match:{or:[{equals:"primeintellect/intellect-3-fp8"},{equals:"primeintellect/intellect-3-fp8-fast"}]},context_window:131072,prices:{input_mtok:.2,output_mtok:1.1}},{id:"Qwen/Qwen2.5-Coder-7B",name:"Qwen2.5-Coder-7B",match:{or:[{equals:"qwen/qwen2.5-coder-7b"},{equals:"qwen/qwen2.5-coder-7b-fast"}]},context_window:32768,prices:{input_mtok:.03,output_mtok:.09}},{id:"Qwen/Qwen2.5-VL-72B-Instruct",name:"Qwen2.5-VL-72B-Instruct",match:{or:[{equals:"qwen/qwen2.5-vl-72b-instruct"},{equals:"qwen/qwen2.5-vl-72b-instruct-fast"}]},context_window:32e3,prices:{input_mtok:.25,output_mtok:.75}},{id:"Qwen/Qwen3-235B-A22B-Instruct-2507",name:"Qwen3-235B-A22B-Instruct-2507",match:{or:[{equals:"qwen/qwen3-235b-a22b-instruct-2507"},{equals:"qwen/qwen3-235b-a22b-instruct-2507-fast"}]},context_window:262144,prices:{input_mtok:.2,output_mtok:.6}},{id:"Qwen/Qwen3-235B-A22B-Thinking-2507",name:"Qwen3-235B-A22B-Thinking-2507",match:{or:[{equals:"qwen/qwen3-235b-a22b-thinking-2507"},{equals:"qwen/qwen3-235b-a22b-thinking-2507-fast"}]},context_window:262144,prices:{input_mtok:.2,output_mtok:.8}},{id:"Qwen/Qwen3-30B-A3B-Instruct-2507",name:"Qwen3-30B-A3B-Instruct-2507",match:{or:[{equals:"qwen/qwen3-30b-a3b-instruct-2507"},{equals:"qwen/qwen3-30b-a3b-instruct-2507-fast"}]},context_window:262144,prices:{input_mtok:.1,output_mtok:.3}},{id:"Qwen/Qwen3-30B-A3B-Thinking-2507",name:"Qwen3-30B-A3B-Thinking-2507",match:{or:[{equals:"qwen/qwen3-30b-a3b-thinking-2507"},{equals:"qwen/qwen3-30b-a3b-thinking-2507-fast"}]},context_window:262144,prices:{input_mtok:.1,output_mtok:.3}},{id:"Qwen/Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"qwen/qwen3-32b"},{equals:"qwen/qwen3-32b-fast"}]},context_window:40960,prices:{input_mtok:.1,output_mtok:.3}},{id:"Qwen/Qwen3-Coder-30B-A3B-Instruct",name:"Qwen3-Coder-30B-A3B-Instruct",match:{or:[{equals:"qwen/qwen3-coder-30b-a3b-instruct"},{equals:"qwen/qwen3-coder-30b-a3b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.1,output_mtok:.3}},{id:"Qwen/Qwen3-Coder-480B-A35B-Instruct",name:"Qwen3-Coder-480B-A35B-Instruct",match:{or:[{equals:"qwen/qwen3-coder-480b-a35b-instruct"},{equals:"qwen/qwen3-coder-480b-a35b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.4,output_mtok:1.8}},{id:"deepseek-ai/DeepSeek-R1-0528",name:"DeepSeek-R1-0528",match:{or:[{equals:"deepseek-ai/deepseek-r1-0528"},{equals:"deepseek-ai/deepseek-r1-0528-fast"}]},context_window:163840,prices:{input_mtok:.8,output_mtok:2.4}},{id:"deepseek-ai/DeepSeek-V3-0324",name:"DeepSeek-V3-0324",match:{or:[{equals:"deepseek-ai/deepseek-v3-0324"},{equals:"deepseek-ai/deepseek-v3-0324-fast"}]},context_window:32768,prices:{input_mtok:.75,output_mtok:2.25}},{id:"google/gemma-2-2b-it",name:"gemma-2-2b-it",match:{or:[{equals:"google/gemma-2-2b-it"},{equals:"google/gemma-2-2b-it-fast"}]},context_window:8192,prices:{input_mtok:.02,output_mtok:.06}},{id:"google/gemma-2-9b-it",name:"gemma-2-9b-it",match:{or:[{equals:"google/gemma-2-9b-it"},{equals:"google/gemma-2-9b-it-fast"}]},context_window:8192,prices:{input_mtok:.03,output_mtok:.09}},{id:"google/gemma-3-27b-it",name:"gemma-3-27b-it",match:{or:[{equals:"google/gemma-3-27b-it"},{equals:"google/gemma-3-27b-it-fast"}]},context_window:11e4,prices:{input_mtok:.2,output_mtok:.6}},{id:"meta-llama/Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.03,output_mtok:.09}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.25,output_mtok:.75}},{id:"moonshotai/Kimi-K2-Instruct",name:"Kimi-K2-Instruct",match:{or:[{equals:"moonshotai/kimi-k2-instruct"},{equals:"moonshotai/kimi-k2-instruct-fast"}]},context_window:131072,prices:{input_mtok:.5,output_mtok:2.4}},{id:"moonshotai/Kimi-K2-Thinking",name:"Kimi-K2-Thinking",match:{or:[{equals:"moonshotai/kimi-k2-thinking"},{equals:"moonshotai/kimi-k2-thinking-fast"}]},context_window:262144,prices:{input_mtok:.6,output_mtok:2.5}},{id:"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1",name:"Llama-3_1-Nemotron-Ultra-253B-v1",match:{or:[{equals:"nvidia/llama-3_1-nemotron-ultra-253b-v1"},{equals:"nvidia/llama-3_1-nemotron-ultra-253b-v1-fast"}]},context_window:131072,prices:{input_mtok:.6,output_mtok:1.8}},{id:"nvidia/NVIDIA-Nemotron-Nano-12B-v2",name:"NVIDIA-Nemotron-Nano-12B-v2",match:{or:[{equals:"nvidia/nvidia-nemotron-nano-12b-v2"},{equals:"nvidia/nvidia-nemotron-nano-12b-v2-fast"}]},context_window:131072,prices:{input_mtok:.07,output_mtok:.2}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:.6}},{id:"zai-org/GLM-4.5",name:"GLM-4.5",match:{or:[{equals:"zai-org/glm-4.5"},{equals:"zai-org/glm-4.5-fast"}]},context_window:131072,prices:{input_mtok:.6,output_mtok:2.2}},{id:"zai-org/GLM-4.5-Air",name:"GLM-4.5-Air",match:{or:[{equals:"zai-org/glm-4.5-air"},{equals:"zai-org/glm-4.5-air-fast"}]},context_window:131072,prices:{input_mtok:.2,output_mtok:1.2}}]},{id:"huggingface_novita",name:"HuggingFace (novita)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/novita",provider_match:{and:[{contains:"huggingface"},{contains:"novita"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"MiniMaxAI/MiniMax-M1-80k",name:"MiniMax-M1-80k",match:{or:[{equals:"minimaxai/minimax-m1-80k"},{equals:"minimaxai/minimax-m1-80k-fast"}]},context_window:1e6,prices:{input_mtok:.55,output_mtok:2.2}},{id:"MiniMaxAI/MiniMax-M2",name:"MiniMax-M2",match:{or:[{equals:"minimaxai/minimax-m2"},{equals:"minimaxai/minimax-m2-fast"},{equals:"minimaxai/minimax-m2.1"},{equals:"minimaxai/minimax-m2.1-fast"},{equals:"minimaxai/minimax-m2.5"},{equals:"minimaxai/minimax-m2.5-fast"}]},context_window:204800,prices:{input_mtok:.3,output_mtok:1.2}},{id:"NousResearch/Hermes-2-Pro-Llama-3-8B",name:"Hermes-2-Pro-Llama-3-8B",match:{or:[{equals:"nousresearch/hermes-2-pro-llama-3-8b"},{equals:"nousresearch/hermes-2-pro-llama-3-8b-fast"}]},context_window:8192,prices:{input_mtok:.14,output_mtok:.14}},{id:"Qwen/Qwen2.5-72B-Instruct",name:"Qwen2.5-72B-Instruct",match:{or:[{equals:"qwen/qwen2.5-72b-instruct"},{equals:"qwen/qwen2.5-72b-instruct-fast"}]},context_window:32e3,prices:{input_mtok:.38,output_mtok:.4}},{id:"Qwen/Qwen3-235B-A22B",name:"Qwen3-235B-A22B",match:{or:[{equals:"qwen/qwen3-235b-a22b"},{equals:"qwen/qwen3-235b-a22b-fast"}]},context_window:40960,prices:{input_mtok:.2,output_mtok:.8}},{id:"Qwen/Qwen3-235B-A22B-Instruct-2507",name:"Qwen3-235B-A22B-Instruct-2507",match:{or:[{equals:"qwen/qwen3-235b-a22b-instruct-2507"},{equals:"qwen/qwen3-235b-a22b-instruct-2507-fast"}]},context_window:131072,prices:{input_mtok:.09,output_mtok:.58}},{id:"Qwen/Qwen3-235B-A22B-Thinking-2507",name:"Qwen3-235B-A22B-Thinking-2507",match:{or:[{equals:"qwen/qwen3-235b-a22b-thinking-2507"},{equals:"qwen/qwen3-235b-a22b-thinking-2507-fast"}]},context_window:131072,prices:{input_mtok:.3,output_mtok:3}},{id:"Qwen/Qwen3-30B-A3B",name:"Qwen3-30B-A3B",match:{or:[{equals:"qwen/qwen3-30b-a3b"},{equals:"qwen/qwen3-30b-a3b-fast"}]},context_window:40960,prices:{input_mtok:.09,output_mtok:.45}},{id:"Qwen/Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"qwen/qwen3-32b"},{equals:"qwen/qwen3-32b-fast"}]},context_window:40960,prices:{input_mtok:.1,output_mtok:.45}},{id:"Qwen/Qwen3-Coder-480B-A35B-Instruct",name:"Qwen3-Coder-480B-A35B-Instruct",match:{or:[{equals:"qwen/qwen3-coder-480b-a35b-instruct"},{equals:"qwen/qwen3-coder-480b-a35b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.3,output_mtok:1.3}},{id:"Qwen/Qwen3-Coder-Next",name:"Qwen3-Coder-Next",match:{or:[{equals:"qwen/qwen3-coder-next"},{equals:"qwen/qwen3-coder-next-fast"}]},context_window:262144,prices:{input_mtok:.2,output_mtok:1.5}},{id:"Qwen/Qwen3-Next-80B-A3B-Instruct",name:"Qwen3-Next-80B-A3B-Instruct",match:{or:[{equals:"qwen/qwen3-next-80b-a3b-instruct"},{equals:"qwen/qwen3-next-80b-a3b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:1.5}},{id:"Qwen/Qwen3-Next-80B-A3B-Thinking",name:"Qwen3-Next-80B-A3B-Thinking",match:{or:[{equals:"qwen/qwen3-next-80b-a3b-thinking"},{equals:"qwen/qwen3-next-80b-a3b-thinking-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:1.5}},{id:"Qwen/Qwen3-VL-235B-A22B-Instruct",name:"Qwen3-VL-235B-A22B-Instruct",match:{or:[{equals:"qwen/qwen3-vl-235b-a22b-instruct"},{equals:"qwen/qwen3-vl-235b-a22b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.3,output_mtok:1.5}},{id:"Qwen/Qwen3-VL-235B-A22B-Thinking",name:"Qwen3-VL-235B-A22B-Thinking",match:{or:[{equals:"qwen/qwen3-vl-235b-a22b-thinking"},{equals:"qwen/qwen3-vl-235b-a22b-thinking-fast"}]},context_window:131072,prices:{input_mtok:.98,output_mtok:3.95}},{id:"Qwen/Qwen3-VL-30B-A3B-Instruct",name:"Qwen3-VL-30B-A3B-Instruct",match:{or:[{equals:"qwen/qwen3-vl-30b-a3b-instruct"},{equals:"qwen/qwen3-vl-30b-a3b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.2,output_mtok:.7}},{id:"Qwen/Qwen3-VL-30B-A3B-Thinking",name:"Qwen3-VL-30B-A3B-Thinking",match:{or:[{equals:"qwen/qwen3-vl-30b-a3b-thinking"},{equals:"qwen/qwen3-vl-30b-a3b-thinking-fast"}]},context_window:131072,prices:{input_mtok:.2,output_mtok:1}},{id:"Qwen/Qwen3-VL-8B-Instruct",name:"Qwen3-VL-8B-Instruct",match:{or:[{equals:"qwen/qwen3-vl-8b-instruct"},{equals:"qwen/qwen3-vl-8b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.08,output_mtok:.5}},{id:"Qwen/Qwen3.5-122B-A10B",name:"Qwen3.5-122B-A10B",match:{or:[{equals:"qwen/qwen3.5-122b-a10b"},{equals:"qwen/qwen3.5-122b-a10b-fast"}]},context_window:262144,prices:{input_mtok:.4,output_mtok:3.2}},{id:"Qwen/Qwen3.5-27B",name:"Qwen3.5-27B",match:{or:[{equals:"qwen/qwen3.5-27b"},{equals:"qwen/qwen3.5-27b-fast"}]},context_window:262144,prices:{input_mtok:.3,output_mtok:2.4}},{id:"Qwen/Qwen3.5-35B-A3B",name:"Qwen3.5-35B-A3B",match:{or:[{equals:"qwen/qwen3.5-35b-a3b"},{equals:"qwen/qwen3.5-35b-a3b-fast"}]},context_window:262144,prices:{input_mtok:.25,output_mtok:2}},{id:"Qwen/Qwen3.5-397B-A17B",name:"Qwen3.5-397B-A17B",match:{or:[{equals:"qwen/qwen3.5-397b-a17b"},{equals:"qwen/qwen3.5-397b-a17b-fast"}]},context_window:262144,prices:{input_mtok:.6,output_mtok:3.6}},{id:"Sao10K/L3-70B-Euryale-v2.1",name:"L3-70B-Euryale-v2.1",match:{or:[{equals:"sao10k/l3-70b-euryale-v2.1"},{equals:"sao10k/l3-70b-euryale-v2.1-fast"}]},context_window:8192,prices:{input_mtok:1.48,output_mtok:1.48}},{id:"Sao10K/L3-8B-Lunaris-v1",name:"L3-8B-Lunaris-v1",match:{or:[{equals:"sao10k/l3-8b-lunaris-v1"},{equals:"sao10k/l3-8b-lunaris-v1-fast"}]},context_window:8192,prices:{input_mtok:.05,output_mtok:.05}},{id:"Sao10K/L3-8B-Stheno-v3.2",name:"L3-8B-Stheno-v3.2",match:{or:[{equals:"sao10k/l3-8b-stheno-v3.2"},{equals:"sao10k/l3-8b-stheno-v3.2-fast"}]},context_window:8192,prices:{input_mtok:.05,output_mtok:.05}},{id:"XiaomiMiMo/MiMo-V2-Flash",name:"MiMo-V2-Flash",match:{or:[{equals:"xiaomimimo/mimo-v2-flash"},{equals:"xiaomimimo/mimo-v2-flash-fast"}]},context_window:262144,prices:{input_mtok:.1,output_mtok:.3}},{id:"alpindale/WizardLM-2-8x22B",name:"WizardLM-2-8x22B",match:{or:[{equals:"alpindale/wizardlm-2-8x22b"},{equals:"alpindale/wizardlm-2-8x22b-fast"}]},context_window:65535,prices:{input_mtok:.62,output_mtok:.62}},{id:"baidu/ERNIE-4.5-21B-A3B-PT",name:"ERNIE-4.5-21B-A3B-PT",match:{or:[{equals:"baidu/ernie-4.5-21b-a3b-pt"},{equals:"baidu/ernie-4.5-21b-a3b-pt-fast"}]},context_window:12e4,prices:{input_mtok:.07,output_mtok:.28}},{id:"baidu/ERNIE-4.5-300B-A47B-Base-PT",name:"ERNIE-4.5-300B-A47B-Base-PT",match:{or:[{equals:"baidu/ernie-4.5-300b-a47b-base-pt"},{equals:"baidu/ernie-4.5-300b-a47b-base-pt-fast"}]},context_window:123e3,prices:{input_mtok:.28,output_mtok:1.1}},{id:"baidu/ERNIE-4.5-VL-28B-A3B-PT",name:"ERNIE-4.5-VL-28B-A3B-PT",match:{or:[{equals:"baidu/ernie-4.5-vl-28b-a3b-pt"},{equals:"baidu/ernie-4.5-vl-28b-a3b-pt-fast"}]},context_window:3e4,prices:{input_mtok:.14,output_mtok:.56}},{id:"baidu/ERNIE-4.5-VL-424B-A47B-Base-PT",name:"ERNIE-4.5-VL-424B-A47B-Base-PT",match:{or:[{equals:"baidu/ernie-4.5-vl-424b-a47b-base-pt"},{equals:"baidu/ernie-4.5-vl-424b-a47b-base-pt-fast"}]},context_window:123e3,prices:{input_mtok:.42,output_mtok:1.25}},{id:"deepseek-ai/DeepSeek-Prover-V2-671B",name:"DeepSeek-Prover-V2-671B",match:{or:[{equals:"deepseek-ai/deepseek-prover-v2-671b"},{equals:"deepseek-ai/deepseek-prover-v2-671b-fast"}]},context_window:16e4,prices:{input_mtok:.7,output_mtok:2.5}},{id:"deepseek-ai/DeepSeek-R1",name:"DeepSeek-R1",match:{or:[{equals:"deepseek-ai/deepseek-r1"},{equals:"deepseek-ai/deepseek-r1-fast"},{equals:"deepseek-ai/deepseek-r1-0528"},{equals:"deepseek-ai/deepseek-r1-0528-fast"}]},context_window:64e3,prices:{input_mtok:.7,output_mtok:2.5}},{id:"deepseek-ai/DeepSeek-R1-Distill-Llama-70B",name:"DeepSeek-R1-Distill-Llama-70B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-llama-70b"},{equals:"deepseek-ai/deepseek-r1-distill-llama-70b-fast"}]},context_window:8192,prices:{input_mtok:.8,output_mtok:.8}},{id:"deepseek-ai/DeepSeek-V3",name:"DeepSeek-V3",match:{or:[{equals:"deepseek-ai/deepseek-v3"},{equals:"deepseek-ai/deepseek-v3-fast"}]},context_window:64e3,prices:{input_mtok:.4,output_mtok:1.3}},{id:"deepseek-ai/DeepSeek-V3-0324",name:"DeepSeek-V3-0324",match:{or:[{equals:"deepseek-ai/deepseek-v3-0324"},{equals:"deepseek-ai/deepseek-v3-0324-fast"}]},context_window:163840,prices:{input_mtok:.27,output_mtok:1.12}},{id:"deepseek-ai/DeepSeek-V3.1",name:"DeepSeek-V3.1",match:{or:[{equals:"deepseek-ai/deepseek-v3.1"},{equals:"deepseek-ai/deepseek-v3.1-fast"},{equals:"deepseek-ai/deepseek-v3.1-terminus"},{equals:"deepseek-ai/deepseek-v3.1-terminus-fast"}]},context_window:131072,prices:{input_mtok:.27,output_mtok:1}},{id:"deepseek-ai/DeepSeek-V3.2",name:"DeepSeek-V3.2",match:{or:[{equals:"deepseek-ai/deepseek-v3.2"},{equals:"deepseek-ai/deepseek-v3.2-fast"}]},context_window:163840,prices:{input_mtok:.269,output_mtok:.4}},{id:"deepseek-ai/DeepSeek-V3.2-Exp",name:"DeepSeek-V3.2-Exp",match:{or:[{equals:"deepseek-ai/deepseek-v3.2-exp"},{equals:"deepseek-ai/deepseek-v3.2-exp-fast"}]},context_window:163840,prices:{input_mtok:.27,output_mtok:.41}},{id:"meta-llama/Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-fast"}]},context_window:16384,prices:{input_mtok:.02,output_mtok:.05}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.135,output_mtok:.4}},{id:"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",name:"Llama-4-Maverick-17B-128E-Instruct-FP8",match:{or:[{equals:"meta-llama/llama-4-maverick-17b-128e-instruct-fp8"},{equals:"meta-llama/llama-4-maverick-17b-128e-instruct-fp8-fast"}]},context_window:1048576,prices:{input_mtok:.27,output_mtok:.85}},{id:"meta-llama/Llama-4-Scout-17B-16E-Instruct",name:"Llama-4-Scout-17B-16E-Instruct",match:{or:[{equals:"meta-llama/llama-4-scout-17b-16e-instruct"},{equals:"meta-llama/llama-4-scout-17b-16e-instruct-fast"}]},context_window:131072,prices:{input_mtok:.18,output_mtok:.59}},{id:"meta-llama/Meta-Llama-3-70B-Instruct",name:"Meta-Llama-3-70B-Instruct",match:{or:[{equals:"meta-llama/meta-llama-3-70b-instruct"},{equals:"meta-llama/meta-llama-3-70b-instruct-fast"}]},context_window:8192,prices:{input_mtok:.51,output_mtok:.74}},{id:"meta-llama/Meta-Llama-3-8B-Instruct",name:"Meta-Llama-3-8B-Instruct",match:{or:[{equals:"meta-llama/meta-llama-3-8b-instruct"},{equals:"meta-llama/meta-llama-3-8b-instruct-fast"}]},context_window:8192,prices:{input_mtok:.04,output_mtok:.04}},{id:"moonshotai/Kimi-K2-Instruct",name:"Kimi-K2-Instruct",match:{or:[{equals:"moonshotai/kimi-k2-instruct"},{equals:"moonshotai/kimi-k2-instruct-fast"}]},context_window:131072,prices:{input_mtok:.57,output_mtok:2.3}},{id:"moonshotai/Kimi-K2-Instruct-0905",name:"Kimi-K2-Instruct-0905",match:{or:[{equals:"moonshotai/kimi-k2-instruct-0905"},{equals:"moonshotai/kimi-k2-instruct-0905-fast"}]},context_window:262144,prices:{input_mtok:.6,output_mtok:2.5}},{id:"moonshotai/Kimi-K2-Thinking",name:"Kimi-K2-Thinking",match:{or:[{equals:"moonshotai/kimi-k2-thinking"},{equals:"moonshotai/kimi-k2-thinking-fast"}]},context_window:262144,prices:{input_mtok:.6,output_mtok:2.5}},{id:"moonshotai/Kimi-K2.5",name:"Kimi-K2.5",match:{or:[{equals:"moonshotai/kimi-k2.5"},{equals:"moonshotai/kimi-k2.5-fast"}]},context_window:262144,prices:{input_mtok:.6,output_mtok:3}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.05,output_mtok:.25}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.04,output_mtok:.15}},{id:"zai-org/AutoGLM-Phone-9B-Multilingual",name:"AutoGLM-Phone-9B-Multilingual",match:{or:[{equals:"zai-org/autoglm-phone-9b-multilingual"},{equals:"zai-org/autoglm-phone-9b-multilingual-fast"}]},context_window:65536,prices:{input_mtok:.035,output_mtok:.138}},{id:"zai-org/GLM-4-32B-0414",name:"GLM-4-32B-0414",match:{or:[{equals:"zai-org/glm-4-32b-0414"},{equals:"zai-org/glm-4-32b-0414-fast"}]},context_window:32e3,prices:{input_mtok:.55,output_mtok:1.66}},{id:"zai-org/GLM-4.5",name:"GLM-4.5",match:{or:[{equals:"zai-org/glm-4.5"},{equals:"zai-org/glm-4.5-fast"}]},context_window:131072,prices:{input_mtok:.6,output_mtok:2.2}},{id:"zai-org/GLM-4.5-Air",name:"GLM-4.5-Air",match:{or:[{equals:"zai-org/glm-4.5-air"},{equals:"zai-org/glm-4.5-air-fast"}]},context_window:131072,prices:{input_mtok:.13,output_mtok:.85}},{id:"zai-org/GLM-4.5V",name:"GLM-4.5V",match:{or:[{equals:"zai-org/glm-4.5v"},{equals:"zai-org/glm-4.5v-fast"}]},context_window:65536,prices:{input_mtok:.6,output_mtok:1.8}},{id:"zai-org/GLM-4.6",name:"GLM-4.6",match:{or:[{equals:"zai-org/glm-4.6"},{equals:"zai-org/glm-4.6-fast"}]},context_window:204800,prices:{input_mtok:.55,output_mtok:2.2}},{id:"zai-org/GLM-4.6V-Flash",name:"GLM-4.6V-Flash",match:{or:[{equals:"zai-org/glm-4.6v-flash"},{equals:"zai-org/glm-4.6v-flash-fast"}]},context_window:131072,prices:{input_mtok:.3,output_mtok:.9}},{id:"zai-org/GLM-4.7",name:"GLM-4.7",match:{or:[{equals:"zai-org/glm-4.7"},{equals:"zai-org/glm-4.7-fast"}]},context_window:204800,prices:{input_mtok:.6,output_mtok:2.2}},{id:"zai-org/GLM-4.7-Flash",name:"GLM-4.7-Flash",match:{or:[{equals:"zai-org/glm-4.7-flash"},{equals:"zai-org/glm-4.7-flash-fast"}]},context_window:2e5,prices:{input_mtok:.07,output_mtok:.4}},{id:"zai-org/GLM-5",name:"GLM-5",match:{or:[{equals:"zai-org/glm-5"},{equals:"zai-org/glm-5-fast"}]},context_window:202800,prices:{input_mtok:1,output_mtok:3.2}}]},{id:"huggingface_nscale",name:"HuggingFace (nscale)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/nscale",provider_match:{and:[{contains:"huggingface"},{contains:"nscale"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"Qwen/QwQ-32B",name:"QwQ-32B",match:{or:[{equals:"qwen/qwq-32b"},{equals:"qwen/qwq-32b-fast"}]},context_window:131072,prices:{input_mtok:.18,output_mtok:.2}},{id:"Qwen/Qwen2.5-Coder-32B-Instruct",name:"Qwen2.5-Coder-32B-Instruct",match:{or:[{equals:"qwen/qwen2.5-coder-32b-instruct"},{equals:"qwen/qwen2.5-coder-32b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.06,output_mtok:.2}},{id:"Qwen/Qwen2.5-Coder-3B-Instruct",name:"Qwen2.5-Coder-3B-Instruct",match:{or:[{equals:"qwen/qwen2.5-coder-3b-instruct"},{equals:"qwen/qwen2.5-coder-3b-instruct-fast"}]},context_window:32768,prices:{input_mtok:.01,output_mtok:.03}},{id:"Qwen/Qwen2.5-Coder-7B-Instruct",name:"Qwen2.5-Coder-7B-Instruct",match:{or:[{equals:"qwen/qwen2.5-coder-7b-instruct"},{equals:"qwen/qwen2.5-coder-7b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.01,output_mtok:.03}},{id:"Qwen/Qwen3-14B",name:"Qwen3-14B",match:{or:[{equals:"qwen/qwen3-14b"},{equals:"qwen/qwen3-14b-fast"}]},context_window:40960,prices:{input_mtok:.07,output_mtok:.2}},{id:"Qwen/Qwen3-235B-A22B",name:"Qwen3-235B-A22B",match:{or:[{equals:"qwen/qwen3-235b-a22b"},{equals:"qwen/qwen3-235b-a22b-fast"},{equals:"qwen/qwen3-235b-a22b-instruct-2507"},{equals:"qwen/qwen3-235b-a22b-instruct-2507-fast"}]},context_window:32e3,prices:{input_mtok:.2,output_mtok:.6}},{id:"Qwen/Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"qwen/qwen3-32b"},{equals:"qwen/qwen3-32b-fast"}]},context_window:40960,prices:{input_mtok:.08,output_mtok:.25}},{id:"Qwen/Qwen3-4B-Instruct-2507",name:"Qwen3-4B-Instruct-2507",match:{or:[{equals:"qwen/qwen3-4b-instruct-2507"},{equals:"qwen/qwen3-4b-instruct-2507-fast"}]},context_window:262144,prices:{input_mtok:.01,output_mtok:.03}},{id:"Qwen/Qwen3-4B-Thinking-2507",name:"Qwen3-4B-Thinking-2507",match:{or:[{equals:"qwen/qwen3-4b-thinking-2507"},{equals:"qwen/qwen3-4b-thinking-2507-fast"}]},context_window:262144,prices:{input_mtok:.01,output_mtok:.03}},{id:"Qwen/Qwen3-8B",name:"Qwen3-8B",match:{or:[{equals:"qwen/qwen3-8b"},{equals:"qwen/qwen3-8b-fast"}]},context_window:40960,prices:{input_mtok:.07,output_mtok:.18}},{id:"deepseek-ai/DeepSeek-R1-Distill-Llama-70B",name:"DeepSeek-R1-Distill-Llama-70B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-llama-70b"},{equals:"deepseek-ai/deepseek-r1-distill-llama-70b-fast"}]},context_window:131072,prices:{input_mtok:.75,output_mtok:.75}},{id:"deepseek-ai/DeepSeek-R1-Distill-Llama-8B",name:"DeepSeek-R1-Distill-Llama-8B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-llama-8b"},{equals:"deepseek-ai/deepseek-r1-distill-llama-8b-fast"}]},context_window:131072,prices:{input_mtok:.05,output_mtok:.05}},{id:"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",name:"DeepSeek-R1-Distill-Qwen-1.5B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-qwen-1.5b"},{equals:"deepseek-ai/deepseek-r1-distill-qwen-1.5b-fast"}]},context_window:131072,prices:{input_mtok:.1,output_mtok:.1}},{id:"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",name:"DeepSeek-R1-Distill-Qwen-32B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-qwen-32b"},{equals:"deepseek-ai/deepseek-r1-distill-qwen-32b-fast"}]},context_window:131072,prices:{input_mtok:.3,output_mtok:.3}},{id:"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",name:"DeepSeek-R1-Distill-Qwen-7B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-qwen-7b"},{equals:"deepseek-ai/deepseek-r1-distill-qwen-7b-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:.15}},{id:"meta-llama/Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.06,output_mtok:.06}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.4,output_mtok:.4}},{id:"meta-llama/Llama-4-Scout-17B-16E-Instruct",name:"Llama-4-Scout-17B-16E-Instruct",match:{or:[{equals:"meta-llama/llama-4-scout-17b-16e-instruct"},{equals:"meta-llama/llama-4-scout-17b-16e-instruct-fast"}]},context_window:89e4,prices:{input_mtok:.09,output_mtok:.29}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.1,output_mtok:.4}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.05,output_mtok:.2}}]},{id:"huggingface_ovhcloud",name:"HuggingFace (ovhcloud)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/ovhcloud",provider_match:{and:[{contains:"huggingface"},{contains:"ovhcloud"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"Qwen/Qwen2.5-VL-72B-Instruct",name:"Qwen2.5-VL-72B-Instruct",match:{or:[{equals:"qwen/qwen2.5-vl-72b-instruct"},{equals:"qwen/qwen2.5-vl-72b-instruct-fast"}]},context_window:32768,prices:{input_mtok:1.01,output_mtok:1.01}},{id:"Qwen/Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"qwen/qwen3-32b"},{equals:"qwen/qwen3-32b-fast"}]},context_window:32768,prices:{input_mtok:.09,output_mtok:.25}},{id:"Qwen/Qwen3-Coder-30B-A3B-Instruct",name:"Qwen3-Coder-30B-A3B-Instruct",match:{or:[{equals:"qwen/qwen3-coder-30b-a3b-instruct"},{equals:"qwen/qwen3-coder-30b-a3b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.07,output_mtok:.26}},{id:"meta-llama/Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.11,output_mtok:.11}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.74,output_mtok:.74}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.09,output_mtok:.47}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.05,output_mtok:.18}}]},{id:"huggingface_publicai",name:"HuggingFace (publicai)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/publicai",provider_match:{and:[{contains:"huggingface"},{contains:"publicai"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"aisingapore/Gemma-SEA-LION-v4-27B-IT",name:"Gemma-SEA-LION-v4-27B-IT",match:{or:[{equals:"aisingapore/gemma-sea-lion-v4-27b-it"},{equals:"aisingapore/gemma-sea-lion-v4-27b-it-fast"}]},prices:{input_mtok:.2,output_mtok:.4}},{id:"aisingapore/Qwen-SEA-LION-v4-32B-IT",name:"Qwen-SEA-LION-v4-32B-IT",match:{or:[{equals:"aisingapore/qwen-sea-lion-v4-32b-it"},{equals:"aisingapore/qwen-sea-lion-v4-32b-it-fast"}]},prices:{input_mtok:.25,output_mtok:.5}},{id:"allenai/Olmo-3-7B-Instruct",name:"Olmo-3-7B-Instruct",match:{or:[{equals:"allenai/olmo-3-7b-instruct"},{equals:"allenai/olmo-3-7b-instruct-fast"}]},prices:{input_mtok:.1,output_mtok:.2}},{id:"allenai/Olmo-3.1-32B-Instruct",name:"Olmo-3.1-32B-Instruct",match:{or:[{equals:"allenai/olmo-3.1-32b-instruct"},{equals:"allenai/olmo-3.1-32b-instruct-fast"}]},prices:{input_mtok:.2,output_mtok:.6}},{id:"dicta-il/DictaLM-3.0-24B-Thinking",name:"DictaLM-3.0-24B-Thinking",match:{or:[{equals:"dicta-il/dictalm-3.0-24b-thinking"},{equals:"dicta-il/dictalm-3.0-24b-thinking-fast"}]},prices:{input_mtok:.2,output_mtok:.4}},{id:"swiss-ai/Apertus-70B-Instruct-2509",name:"Apertus-70B-Instruct-2509",match:{or:[{equals:"swiss-ai/apertus-70b-instruct-2509"},{equals:"swiss-ai/apertus-70b-instruct-2509-fast"}]},prices:{input_mtok:.82,output_mtok:2.92}},{id:"swiss-ai/Apertus-8B-Instruct-2509",name:"Apertus-8B-Instruct-2509",match:{or:[{equals:"swiss-ai/apertus-8b-instruct-2509"},{equals:"swiss-ai/apertus-8b-instruct-2509-fast"}]},prices:{input_mtok:.1,output_mtok:.2}},{id:"utter-project/EuroLLM-22B-Instruct-2512",name:"EuroLLM-22B-Instruct-2512",match:{or:[{equals:"utter-project/eurollm-22b-instruct-2512"},{equals:"utter-project/eurollm-22b-instruct-2512-fast"}]},prices:{input_mtok:.1,output_mtok:.2}}]},{id:"huggingface_sambanova",name:"HuggingFace (sambanova)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/sambanova",provider_match:{and:[{contains:"huggingface"},{contains:"sambanova"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"Qwen/Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"qwen/qwen3-32b"},{equals:"qwen/qwen3-32b-fast"}]},context_window:32768,prices:{input_mtok:.4,output_mtok:.8}},{id:"deepseek-ai/DeepSeek-R1-0528",name:"DeepSeek-R1-0528",match:{or:[{equals:"deepseek-ai/deepseek-r1-0528"},{equals:"deepseek-ai/deepseek-r1-0528-fast"}]},context_window:131072,prices:{input_mtok:5,output_mtok:7}},{id:"deepseek-ai/DeepSeek-R1-Distill-Llama-70B",name:"DeepSeek-R1-Distill-Llama-70B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-llama-70b"},{equals:"deepseek-ai/deepseek-r1-distill-llama-70b-fast"}]},context_window:131072,prices:{input_mtok:.7,output_mtok:1.4}},{id:"deepseek-ai/DeepSeek-V3-0324",name:"DeepSeek-V3-0324",match:{or:[{equals:"deepseek-ai/deepseek-v3-0324"},{equals:"deepseek-ai/deepseek-v3-0324-fast"}]},context_window:131072,prices:{input_mtok:3,output_mtok:4.5}},{id:"meta-llama/Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-fast"}]},context_window:16384,prices:{input_mtok:.1,output_mtok:.2}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.6,output_mtok:1.2}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.22,output_mtok:.59}},{id:"tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4",name:"Llama-3.3-Swallow-70B-Instruct-v0.4",match:{or:[{equals:"tokyotech-llm/llama-3.3-swallow-70b-instruct-v0.4"},{equals:"tokyotech-llm/llama-3.3-swallow-70b-instruct-v0.4-fast"}]},context_window:131072,prices:{input_mtok:.6,output_mtok:1.2}}]},{id:"huggingface_together",name:"HuggingFace (together)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/together",provider_match:{and:[{contains:"huggingface"},{contains:"together"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"EssentialAI/rnj-1-instruct",name:"rnj-1-instruct",match:{or:[{equals:"essentialai/rnj-1-instruct"},{equals:"essentialai/rnj-1-instruct-fast"}]},context_window:32768,prices:{input_mtok:.15,output_mtok:.15}},{id:"Qwen/Qwen2.5-7B-Instruct",name:"Qwen2.5-7B-Instruct",match:{or:[{equals:"qwen/qwen2.5-7b-instruct"},{equals:"qwen/qwen2.5-7b-instruct-fast"}]},context_window:32768,prices:{input_mtok:.3,output_mtok:.3}},{id:"Qwen/Qwen3-235B-A22B-Instruct-2507",name:"Qwen3-235B-A22B-Instruct-2507",match:{or:[{equals:"qwen/qwen3-235b-a22b-instruct-2507"},{equals:"qwen/qwen3-235b-a22b-instruct-2507-fast"}]},context_window:262144,prices:{input_mtok:.2,output_mtok:.6}},{id:"Qwen/Qwen3-Coder-480B-A35B-Instruct",name:"Qwen3-Coder-480B-A35B-Instruct",match:{or:[{equals:"qwen/qwen3-coder-480b-a35b-instruct"},{equals:"qwen/qwen3-coder-480b-a35b-instruct-fast"},{equals:"qwen/qwen3-coder-480b-a35b-instruct-fp8"},{equals:"qwen/qwen3-coder-480b-a35b-instruct-fp8-fast"}]},context_window:262144,prices:{input_mtok:2,output_mtok:2}},{id:"Qwen/Qwen3-Coder-Next-FP8",name:"Qwen3-Coder-Next-FP8",match:{or:[{equals:"qwen/qwen3-coder-next-fp8"},{equals:"qwen/qwen3-coder-next-fp8-fast"}]},context_window:262144,prices:{input_mtok:.5,output_mtok:1.2}},{id:"Qwen/Qwen3-Next-80B-A3B-Instruct",name:"Qwen3-Next-80B-A3B-Instruct",match:{or:[{equals:"qwen/qwen3-next-80b-a3b-instruct"},{equals:"qwen/qwen3-next-80b-a3b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.15,output_mtok:1.5}},{id:"Qwen/Qwen3-VL-8B-Instruct",name:"Qwen3-VL-8B-Instruct",match:{or:[{equals:"qwen/qwen3-vl-8b-instruct"},{equals:"qwen/qwen3-vl-8b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.18000000000000002,output_mtok:.68}},{id:"Qwen/Qwen3.5-397B-A17B",name:"Qwen3.5-397B-A17B",match:{or:[{equals:"qwen/qwen3.5-397b-a17b"},{equals:"qwen/qwen3.5-397b-a17b-fast"}]},context_window:262144,prices:{input_mtok:.6,output_mtok:3.6}},{id:"Qwen/Qwen3.5-9B",name:"Qwen3.5-9B",match:{or:[{equals:"qwen/qwen3.5-9b"},{equals:"qwen/qwen3.5-9b-fast"}]},context_window:262144,prices:{input_mtok:.1,output_mtok:.15}},{id:"ServiceNow-AI/Apriel-1.6-15b-Thinker",name:"Apriel-1.6-15b-Thinker",match:{or:[{equals:"servicenow-ai/apriel-1.6-15b-thinker"},{equals:"servicenow-ai/apriel-1.6-15b-thinker-fast"}]},context_window:131072,prices:{}},{id:"deepcogito/cogito-671b-v2.1",name:"cogito-671b-v2.1",match:{or:[{equals:"deepcogito/cogito-671b-v2.1"},{equals:"deepcogito/cogito-671b-v2.1-fast"},{equals:"deepcogito/cogito-671b-v2.1-fp8"},{equals:"deepcogito/cogito-671b-v2.1-fp8-fast"}]},context_window:163840,prices:{input_mtok:1.25,output_mtok:1.25}},{id:"deepseek-ai/DeepSeek-R1",name:"DeepSeek-R1",match:{or:[{equals:"deepseek-ai/deepseek-r1"},{equals:"deepseek-ai/deepseek-r1-fast"},{equals:"deepseek-ai/deepseek-r1-0528"},{equals:"deepseek-ai/deepseek-r1-0528-fast"}]},context_window:163840,prices:{input_mtok:3,output_mtok:7}},{id:"deepseek-ai/DeepSeek-V3",name:"DeepSeek-V3",match:{or:[{equals:"deepseek-ai/deepseek-v3"},{equals:"deepseek-ai/deepseek-v3-fast"},{equals:"deepseek-ai/deepseek-v3-0324"},{equals:"deepseek-ai/deepseek-v3-0324-fast"}]},context_window:131072,prices:{input_mtok:1.25,output_mtok:1.25}},{id:"deepseek-ai/DeepSeek-V3.1",name:"DeepSeek-V3.1",match:{or:[{equals:"deepseek-ai/deepseek-v3.1"},{equals:"deepseek-ai/deepseek-v3.1-fast"}]},context_window:131072,prices:{input_mtok:.6,output_mtok:1.7}},{id:"google/gemma-3n-E4B-it",name:"gemma-3n-E4B-it",match:{or:[{equals:"google/gemma-3n-e4b-it"},{equals:"google/gemma-3n-e4b-it-fast"}]},context_window:32768,prices:{input_mtok:.02,output_mtok:.04}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.88,output_mtok:.88}},{id:"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",name:"Llama-4-Maverick-17B-128E-Instruct-FP8",match:{or:[{equals:"meta-llama/llama-4-maverick-17b-128e-instruct-fp8"},{equals:"meta-llama/llama-4-maverick-17b-128e-instruct-fp8-fast"}]},context_window:1048576,prices:{input_mtok:.27,output_mtok:.85}},{id:"moonshotai/Kimi-K2.5",name:"Kimi-K2.5",match:{or:[{equals:"moonshotai/kimi-k2.5"},{equals:"moonshotai/kimi-k2.5-fast"}]},context_window:262144,prices:{input_mtok:.5,output_mtok:2.8}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:.6}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.05,output_mtok:.2}},{id:"zai-org/GLM-4.5-Air-FP8",name:"GLM-4.5-Air-FP8",match:{or:[{equals:"zai-org/glm-4.5-air-fp8"},{equals:"zai-org/glm-4.5-air-fp8-fast"}]},context_window:131072,prices:{input_mtok:.2,output_mtok:1.1}},{id:"zai-org/GLM-4.6",name:"GLM-4.6",match:{or:[{equals:"zai-org/glm-4.6"},{equals:"zai-org/glm-4.6-fast"}]},context_window:202752,prices:{input_mtok:.6,output_mtok:2.2}},{id:"zai-org/GLM-4.7-FP8",name:"GLM-4.7-FP8",match:{or:[{equals:"zai-org/glm-4.7-fp8"},{equals:"zai-org/glm-4.7-fp8-fast"}]},context_window:202752,prices:{input_mtok:.45,output_mtok:2}},{id:"zai-org/GLM-5",name:"GLM-5",match:{or:[{equals:"zai-org/glm-5"},{equals:"zai-org/glm-5-fast"}]},context_window:202752,prices:{input_mtok:1,output_mtok:3.2}}]},{id:"minimax",name:"MiniMax",pricing_urls:["https://platform.minimax.io/docs/guides/pricing-paygo"],api_pattern:"https://api\\.minimax(i)?\\.(?:com|io)",price_comments:"Prices sourced from MiniMax international platform USD pricing (platform.minimax.io, May 2026). M2.1, M2.1-highspeed, and M2 are legacy models; prices inferred from CNY pricing at the equivalent 7.00 CNY/USD rate used by the international platform for current models.",model_match:{or:[{starts_with:"MiniMax-M"},{starts_with:"minimax-m"},{equals:"M2-her"},{equals:"m2-her"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"M2-her",name:"MiniMax M2-her",description:"MiniMax M2-her, a text dialogue model optimized for role-playing and multi-turn conversations. 64,000 token context window. No cache support.",match:{or:[{equals:"M2-her"},{equals:"m2-her"}]},context_window:64e3,prices:{input_mtok:.3,output_mtok:1.2}},{id:"MiniMax-M2",name:"MiniMax M2",description:"MiniMax M2 (legacy), a multimodal language model with 204,800 token context window. Supports agentic capabilities and advanced reasoning.",match:{or:[{equals:"MiniMax-M2"},{equals:"minimax-m2"},{equals:"MiniMax-M2.1"},{equals:"minimax-m2.1"},{equals:"MiniMax-M2.5"},{equals:"minimax-m2.5"}]},context_window:204800,prices:{input_mtok:.3,cache_write_mtok:.375,cache_read_mtok:.03,output_mtok:1.2}},{id:"MiniMax-M2.1-highspeed",name:"MiniMax M2.1 Highspeed",description:"MiniMax M2.1 highspeed variant (legacy) with higher throughput.",match:{or:[{contains:"M2.1-highspeed"},{contains:"m2.1-highspeed"}]},context_window:204800,prices:{input_mtok:.6,cache_write_mtok:.375,cache_read_mtok:.03,output_mtok:2.4}},{id:"MiniMax-M2.5-highspeed",name:"MiniMax M2.5 Highspeed",description:"MiniMax M2.5 highspeed variant with higher throughput.",match:{or:[{contains:"M2.5-highspeed"},{contains:"m2.5-highspeed"}]},context_window:204800,prices:{input_mtok:.6,cache_write_mtok:.375,cache_read_mtok:.03,output_mtok:2.4}},{id:"MiniMax-M2.7",name:"MiniMax M2.7",description:"MiniMax M2.7, a multimodal language model with 204,800 token context window. Achieves top performance in real-world engineering, office productivity, and character-rich interaction.",match:{or:[{equals:"MiniMax-M2.7"},{equals:"minimax-m2.7"}]},context_window:204800,prices:{input_mtok:.3,cache_write_mtok:.375,cache_read_mtok:.06,output_mtok:1.2}},{id:"MiniMax-M2.7-highspeed",name:"MiniMax M2.7 Highspeed",description:"MiniMax M2.7 highspeed variant with higher throughput.",match:{or:[{contains:"M2.7-highspeed"},{contains:"m2.7-highspeed"}]},context_window:204800,prices:{input_mtok:.6,cache_write_mtok:.375,cache_read_mtok:.06,output_mtok:2.4}}]},{id:"mistral",name:"Mistral",pricing_urls:["https://mistral.ai/pricing#api-pricing"],api_pattern:"https://api\\.mistral\\.ai",model_match:{regex:"(?:mi|code|dev|magi|mini)stral"},provider_match:{starts_with:"mistral"},extractors:[{api_flavor:"default",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"codestral",name:"Codestral",description:"Mistral's cutting-edge language model for coding. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.",match:{or:[{equals:"codestral-latest"},{equals:"codestral-2501"}]},prices:{input_mtok:.3,output_mtok:.9}},{id:"devstral-small",name:"Devstral Small",description:"Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%).",match:{equals:"devstral-small"},prices:{input_mtok:.06,output_mtok:.12}},{id:"devstral-small:free",name:"Devstral Small (free)",description:"Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%).",match:{equals:"devstral-small:free"},prices:{}},{id:"magistral-medium",name:"Magistral Medium",description:"Magistral is Mistral's first reasoning model. It is ideal for general purpose use requiring longer thought processing and better accuracy than with non-reasoning LLMs. From legal research and financial forecasting to software development and creative storytelling — this model solves multi-step challenges where transparency and precision are critical.",match:{or:[{starts_with:"magistral-medium"}]},prices:{input_mtok:2,output_mtok:5}},{id:"magistral-small",name:"Magistral Small",description:"Magistral Small is a 24B parameter instruction-tuned model based on Mistral-Small-3.1 (2503), enhanced through supervised fine-tuning on traces from Magistral Medium and further refined via reinforcement learning. It is optimized for reasoning and supports a wide multilingual range, including over 20 languages.",match:{starts_with:"magistral-small-"},prices:{input_mtok:.5,output_mtok:1.5}},{id:"ministral-3b",name:"Ministral 3B",description:"Ministral 3B is a 3B parameter model optimized for on-device and edge computing. It excels in knowledge, commonsense reasoning, and function-calling, outperforming larger models like Mistral 7B on most benchmarks. Supporting up to 128k context length, it's ideal for orchestrating agentic workflows and specialist tasks with efficient inference.",match:{equals:"ministral-3b"},prices:{input_mtok:.04,output_mtok:.04}},{id:"ministral-8b",name:"Ministral 8B 24.10",description:"Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect for low-latency, privacy-first applications.",match:{starts_with:"ministral-8b"},prices:{input_mtok:.1,output_mtok:1}},{id:"mistral-7b",name:"Mistral 7B",match:{or:[{equals:"mistral-7b"},{equals:"open-mistral-7b"}]},prices:{input_mtok:.25,output_mtok:.25}},{id:"mistral-embed",match:{equals:"mistral-embed"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistral-large",name:"Mistral Large",description:"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here.",match:{or:[{equals:"mistral-large"},{equals:"mistral-large-latest"},{equals:"mistral-large-2407"},{equals:"mistral-large-2411"}]},prices:{input_mtok:2,output_mtok:6}},{id:"mistral-medium-3",name:"Mistral Medium 3",description:"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.",match:{starts_with:"mistral-medium"},prices:{input_mtok:.4,output_mtok:2}},{id:"mistral-nemo",name:"Mistral NeMo",description:"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.",match:{or:[{equals:"mistral-nemo"},{equals:"open-mistral-nemo"}]},prices:{input_mtok:.15,output_mtok:.15}},{id:"mistral-nemo:free",name:"Mistral Nemo (free)",description:"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.",match:{equals:"mistral-nemo:free"},prices:{}},{id:"mistral-saba",name:"Mistral Saba",description:"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional datasets, it supports multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. This makes it a versatile option for a range of regional and multilingual applications. Read more at the blog post here",match:{or:[{equals:"mistral-saba"},{equals:"mistral-saba-latest"}]},prices:{input_mtok:.2,output_mtok:.6}},{id:"mistral-small-24b-instruct-2501",name:"Mistral Small 3",description:"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment.",match:{equals:"mistral-small-24b-instruct-2501"},price_comments:"Can't find pricing on this model, so just trusting open router",prices:{input_mtok:.05,output_mtok:.08}},{id:"mistral-small-24b-instruct-2501:free",name:"Mistral Small 3 (free)",description:"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment.",match:{equals:"mistral-small-24b-instruct-2501:free"},prices:{}},{id:"mistral-small-latest",name:"Mistral Small 3.2",description:"SOTA. Multimodal. Multilingual. Apache 2.0.",match:{equals:"mistral-small-latest"},prices:{input_mtok:.1,output_mtok:.3}},{id:"mistral-tiny",name:"Mistral Tiny",description:"Note: This model is being deprecated. Recommended replacement is the newer Ministral 8B",match:{equals:"mistral-tiny"},prices:{input_mtok:.25,output_mtok:.25},deprecated:!0},{id:"mixtral-8x22b-instruct",name:"Mixtral 8x22B Instruct",description:`Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include:
7
+ `,match:{equals:"openai/gpt-oss-20b"},context_window:131072,prices:{input_mtok:.075,cache_read_mtok:.0375,output_mtok:.3}},{id:"qwen/qwen3-32b",name:"Qwen3 32B 131k",match:{equals:"qwen/qwen3-32b"},prices:{input_mtok:.29,output_mtok:.59}}]},{id:"huggingface_cerebras",name:"HuggingFace (cerebras)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/cerebras",provider_match:{and:[{contains:"huggingface"},{contains:"cerebras"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"meta-llama/Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-fast"}]},prices:{input_mtok:.1,output_mtok:.1}}]},{id:"huggingface_fireworks-ai",name:"HuggingFace (fireworks-ai)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/fireworks-ai",provider_match:{and:[{contains:"huggingface"},{contains:"fireworks-ai"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.9,output_mtok:.9}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:.6}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.05,output_mtok:.2}}]},{id:"huggingface_groq",name:"HuggingFace (groq)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/groq",provider_match:{and:[{contains:"huggingface"},{contains:"groq"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"Qwen/Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"qwen/qwen3-32b"},{equals:"qwen/qwen3-32b-fast"}]},context_window:131072,prices:{input_mtok:.29,output_mtok:.59}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.59,output_mtok:.79}},{id:"meta-llama/Llama-4-Scout-17B-16E-Instruct",name:"Llama-4-Scout-17B-16E-Instruct",match:{or:[{equals:"meta-llama/llama-4-scout-17b-16e-instruct"},{equals:"meta-llama/llama-4-scout-17b-16e-instruct-fast"}]},context_window:131072,prices:{input_mtok:.11,output_mtok:.34}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:.75}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.1,output_mtok:.5}}]},{id:"huggingface_hyperbolic",name:"HuggingFace (hyperbolic)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/hyperbolic",provider_match:{and:[{contains:"huggingface"},{contains:"hyperbolic"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"Qwen/Qwen2.5-VL-72B-Instruct",name:"Qwen2.5-VL-72B-Instruct",match:{or:[{equals:"qwen/qwen2.5-vl-72b-instruct"},{equals:"qwen/qwen2.5-vl-72b-instruct-fast"}]},context_window:32768,prices:{input_mtok:.6,output_mtok:.6}},{id:"Qwen/Qwen2.5-VL-7B-Instruct",name:"Qwen2.5-VL-7B-Instruct",match:{or:[{equals:"qwen/qwen2.5-vl-7b-instruct"},{equals:"qwen/qwen2.5-vl-7b-instruct-fast"}]},context_window:32768,prices:{input_mtok:.2,output_mtok:.2}},{id:"Qwen/Qwen3-235B-A22B-Instruct-2507",name:"Qwen3-235B-A22B-Instruct-2507",match:{or:[{equals:"qwen/qwen3-235b-a22b-instruct-2507"},{equals:"qwen/qwen3-235b-a22b-instruct-2507-fast"}]},context_window:262144,prices:{input_mtok:2,output_mtok:2}},{id:"Qwen/Qwen3-Coder-480B-A35B-Instruct",name:"Qwen3-Coder-480B-A35B-Instruct",match:{or:[{equals:"qwen/qwen3-coder-480b-a35b-instruct"},{equals:"qwen/qwen3-coder-480b-a35b-instruct-fast"}]},context_window:262144,prices:{input_mtok:2,output_mtok:2}},{id:"Qwen/Qwen3-Next-80B-A3B-Instruct",name:"Qwen3-Next-80B-A3B-Instruct",match:{or:[{equals:"qwen/qwen3-next-80b-a3b-instruct"},{equals:"qwen/qwen3-next-80b-a3b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.3,output_mtok:.3}},{id:"Qwen/Qwen3-Next-80B-A3B-Thinking",name:"Qwen3-Next-80B-A3B-Thinking",match:{or:[{equals:"qwen/qwen3-next-80b-a3b-thinking"},{equals:"qwen/qwen3-next-80b-a3b-thinking-fast"}]},context_window:262144,prices:{input_mtok:.3,output_mtok:.3}},{id:"deepseek-ai/DeepSeek-R1",name:"DeepSeek-R1",match:{or:[{equals:"deepseek-ai/deepseek-r1"},{equals:"deepseek-ai/deepseek-r1-fast"}]},context_window:163840,prices:{input_mtok:2,output_mtok:2}},{id:"deepseek-ai/DeepSeek-R1-0528",name:"DeepSeek-R1-0528",match:{or:[{equals:"deepseek-ai/deepseek-r1-0528"},{equals:"deepseek-ai/deepseek-r1-0528-fast"}]},context_window:163840,prices:{input_mtok:3,output_mtok:3}},{id:"deepseek-ai/DeepSeek-V3-0324",name:"DeepSeek-V3-0324",match:{or:[{equals:"deepseek-ai/deepseek-v3-0324"},{equals:"deepseek-ai/deepseek-v3-0324-fast"}]},context_window:163840,prices:{input_mtok:1.25,output_mtok:1.25}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.4,output_mtok:.4}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.3,output_mtok:.3}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.1,output_mtok:.1}}]},{id:"huggingface_nebius",name:"HuggingFace (nebius)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/nebius",provider_match:{and:[{contains:"huggingface"},{contains:"nebius"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"NousResearch/Hermes-4-405B",name:"Hermes-4-405B",match:{or:[{equals:"nousresearch/hermes-4-405b"},{equals:"nousresearch/hermes-4-405b-fast"}]},context_window:131072,prices:{input_mtok:1,output_mtok:3}},{id:"NousResearch/Hermes-4-70B",name:"Hermes-4-70B",match:{or:[{equals:"nousresearch/hermes-4-70b"},{equals:"nousresearch/hermes-4-70b-fast"}]},context_window:131072,prices:{input_mtok:.13,output_mtok:.4}},{id:"PrimeIntellect/INTELLECT-3-FP8",name:"INTELLECT-3-FP8",match:{or:[{equals:"primeintellect/intellect-3-fp8"},{equals:"primeintellect/intellect-3-fp8-fast"}]},context_window:131072,prices:{input_mtok:.2,output_mtok:1.1}},{id:"Qwen/Qwen2.5-Coder-7B",name:"Qwen2.5-Coder-7B",match:{or:[{equals:"qwen/qwen2.5-coder-7b"},{equals:"qwen/qwen2.5-coder-7b-fast"}]},context_window:32768,prices:{input_mtok:.03,output_mtok:.09}},{id:"Qwen/Qwen2.5-VL-72B-Instruct",name:"Qwen2.5-VL-72B-Instruct",match:{or:[{equals:"qwen/qwen2.5-vl-72b-instruct"},{equals:"qwen/qwen2.5-vl-72b-instruct-fast"}]},context_window:32e3,prices:{input_mtok:.25,output_mtok:.75}},{id:"Qwen/Qwen3-235B-A22B-Instruct-2507",name:"Qwen3-235B-A22B-Instruct-2507",match:{or:[{equals:"qwen/qwen3-235b-a22b-instruct-2507"},{equals:"qwen/qwen3-235b-a22b-instruct-2507-fast"}]},context_window:262144,prices:{input_mtok:.2,output_mtok:.6}},{id:"Qwen/Qwen3-235B-A22B-Thinking-2507",name:"Qwen3-235B-A22B-Thinking-2507",match:{or:[{equals:"qwen/qwen3-235b-a22b-thinking-2507"},{equals:"qwen/qwen3-235b-a22b-thinking-2507-fast"}]},context_window:262144,prices:{input_mtok:.2,output_mtok:.8}},{id:"Qwen/Qwen3-30B-A3B-Instruct-2507",name:"Qwen3-30B-A3B-Instruct-2507",match:{or:[{equals:"qwen/qwen3-30b-a3b-instruct-2507"},{equals:"qwen/qwen3-30b-a3b-instruct-2507-fast"}]},context_window:262144,prices:{input_mtok:.1,output_mtok:.3}},{id:"Qwen/Qwen3-30B-A3B-Thinking-2507",name:"Qwen3-30B-A3B-Thinking-2507",match:{or:[{equals:"qwen/qwen3-30b-a3b-thinking-2507"},{equals:"qwen/qwen3-30b-a3b-thinking-2507-fast"}]},context_window:262144,prices:{input_mtok:.1,output_mtok:.3}},{id:"Qwen/Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"qwen/qwen3-32b"},{equals:"qwen/qwen3-32b-fast"}]},context_window:40960,prices:{input_mtok:.1,output_mtok:.3}},{id:"Qwen/Qwen3-Coder-30B-A3B-Instruct",name:"Qwen3-Coder-30B-A3B-Instruct",match:{or:[{equals:"qwen/qwen3-coder-30b-a3b-instruct"},{equals:"qwen/qwen3-coder-30b-a3b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.1,output_mtok:.3}},{id:"Qwen/Qwen3-Coder-480B-A35B-Instruct",name:"Qwen3-Coder-480B-A35B-Instruct",match:{or:[{equals:"qwen/qwen3-coder-480b-a35b-instruct"},{equals:"qwen/qwen3-coder-480b-a35b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.4,output_mtok:1.8}},{id:"deepseek-ai/DeepSeek-R1-0528",name:"DeepSeek-R1-0528",match:{or:[{equals:"deepseek-ai/deepseek-r1-0528"},{equals:"deepseek-ai/deepseek-r1-0528-fast"}]},context_window:163840,prices:{input_mtok:.8,output_mtok:2.4}},{id:"deepseek-ai/DeepSeek-V3-0324",name:"DeepSeek-V3-0324",match:{or:[{equals:"deepseek-ai/deepseek-v3-0324"},{equals:"deepseek-ai/deepseek-v3-0324-fast"}]},context_window:32768,prices:{input_mtok:.75,output_mtok:2.25}},{id:"google/gemma-2-2b-it",name:"gemma-2-2b-it",match:{or:[{equals:"google/gemma-2-2b-it"},{equals:"google/gemma-2-2b-it-fast"}]},context_window:8192,prices:{input_mtok:.02,output_mtok:.06}},{id:"google/gemma-2-9b-it",name:"gemma-2-9b-it",match:{or:[{equals:"google/gemma-2-9b-it"},{equals:"google/gemma-2-9b-it-fast"}]},context_window:8192,prices:{input_mtok:.03,output_mtok:.09}},{id:"google/gemma-3-27b-it",name:"gemma-3-27b-it",match:{or:[{equals:"google/gemma-3-27b-it"},{equals:"google/gemma-3-27b-it-fast"}]},context_window:11e4,prices:{input_mtok:.2,output_mtok:.6}},{id:"meta-llama/Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.03,output_mtok:.09}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.25,output_mtok:.75}},{id:"moonshotai/Kimi-K2-Instruct",name:"Kimi-K2-Instruct",match:{or:[{equals:"moonshotai/kimi-k2-instruct"},{equals:"moonshotai/kimi-k2-instruct-fast"}]},context_window:131072,prices:{input_mtok:.5,output_mtok:2.4}},{id:"moonshotai/Kimi-K2-Thinking",name:"Kimi-K2-Thinking",match:{or:[{equals:"moonshotai/kimi-k2-thinking"},{equals:"moonshotai/kimi-k2-thinking-fast"}]},context_window:262144,prices:{input_mtok:.6,output_mtok:2.5}},{id:"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1",name:"Llama-3_1-Nemotron-Ultra-253B-v1",match:{or:[{equals:"nvidia/llama-3_1-nemotron-ultra-253b-v1"},{equals:"nvidia/llama-3_1-nemotron-ultra-253b-v1-fast"}]},context_window:131072,prices:{input_mtok:.6,output_mtok:1.8}},{id:"nvidia/NVIDIA-Nemotron-Nano-12B-v2",name:"NVIDIA-Nemotron-Nano-12B-v2",match:{or:[{equals:"nvidia/nvidia-nemotron-nano-12b-v2"},{equals:"nvidia/nvidia-nemotron-nano-12b-v2-fast"}]},context_window:131072,prices:{input_mtok:.07,output_mtok:.2}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:.6}},{id:"zai-org/GLM-4.5",name:"GLM-4.5",match:{or:[{equals:"zai-org/glm-4.5"},{equals:"zai-org/glm-4.5-fast"}]},context_window:131072,prices:{input_mtok:.6,output_mtok:2.2}},{id:"zai-org/GLM-4.5-Air",name:"GLM-4.5-Air",match:{or:[{equals:"zai-org/glm-4.5-air"},{equals:"zai-org/glm-4.5-air-fast"}]},context_window:131072,prices:{input_mtok:.2,output_mtok:1.2}}]},{id:"huggingface_novita",name:"HuggingFace (novita)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/novita",provider_match:{and:[{contains:"huggingface"},{contains:"novita"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"MiniMaxAI/MiniMax-M1-80k",name:"MiniMax-M1-80k",match:{or:[{equals:"minimaxai/minimax-m1-80k"},{equals:"minimaxai/minimax-m1-80k-fast"}]},context_window:1e6,prices:{input_mtok:.55,output_mtok:2.2}},{id:"MiniMaxAI/MiniMax-M2",name:"MiniMax-M2",match:{or:[{equals:"minimaxai/minimax-m2"},{equals:"minimaxai/minimax-m2-fast"},{equals:"minimaxai/minimax-m2.1"},{equals:"minimaxai/minimax-m2.1-fast"},{equals:"minimaxai/minimax-m2.5"},{equals:"minimaxai/minimax-m2.5-fast"}]},context_window:204800,prices:{input_mtok:.3,output_mtok:1.2}},{id:"NousResearch/Hermes-2-Pro-Llama-3-8B",name:"Hermes-2-Pro-Llama-3-8B",match:{or:[{equals:"nousresearch/hermes-2-pro-llama-3-8b"},{equals:"nousresearch/hermes-2-pro-llama-3-8b-fast"}]},context_window:8192,prices:{input_mtok:.14,output_mtok:.14}},{id:"Qwen/Qwen2.5-72B-Instruct",name:"Qwen2.5-72B-Instruct",match:{or:[{equals:"qwen/qwen2.5-72b-instruct"},{equals:"qwen/qwen2.5-72b-instruct-fast"}]},context_window:32e3,prices:{input_mtok:.38,output_mtok:.4}},{id:"Qwen/Qwen3-235B-A22B",name:"Qwen3-235B-A22B",match:{or:[{equals:"qwen/qwen3-235b-a22b"},{equals:"qwen/qwen3-235b-a22b-fast"}]},context_window:40960,prices:{input_mtok:.2,output_mtok:.8}},{id:"Qwen/Qwen3-235B-A22B-Instruct-2507",name:"Qwen3-235B-A22B-Instruct-2507",match:{or:[{equals:"qwen/qwen3-235b-a22b-instruct-2507"},{equals:"qwen/qwen3-235b-a22b-instruct-2507-fast"}]},context_window:131072,prices:{input_mtok:.09,output_mtok:.58}},{id:"Qwen/Qwen3-235B-A22B-Thinking-2507",name:"Qwen3-235B-A22B-Thinking-2507",match:{or:[{equals:"qwen/qwen3-235b-a22b-thinking-2507"},{equals:"qwen/qwen3-235b-a22b-thinking-2507-fast"}]},context_window:131072,prices:{input_mtok:.3,output_mtok:3}},{id:"Qwen/Qwen3-30B-A3B",name:"Qwen3-30B-A3B",match:{or:[{equals:"qwen/qwen3-30b-a3b"},{equals:"qwen/qwen3-30b-a3b-fast"}]},context_window:40960,prices:{input_mtok:.09,output_mtok:.45}},{id:"Qwen/Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"qwen/qwen3-32b"},{equals:"qwen/qwen3-32b-fast"}]},context_window:40960,prices:{input_mtok:.1,output_mtok:.45}},{id:"Qwen/Qwen3-Coder-480B-A35B-Instruct",name:"Qwen3-Coder-480B-A35B-Instruct",match:{or:[{equals:"qwen/qwen3-coder-480b-a35b-instruct"},{equals:"qwen/qwen3-coder-480b-a35b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.3,output_mtok:1.3}},{id:"Qwen/Qwen3-Coder-Next",name:"Qwen3-Coder-Next",match:{or:[{equals:"qwen/qwen3-coder-next"},{equals:"qwen/qwen3-coder-next-fast"}]},context_window:262144,prices:{input_mtok:.2,output_mtok:1.5}},{id:"Qwen/Qwen3-Next-80B-A3B-Instruct",name:"Qwen3-Next-80B-A3B-Instruct",match:{or:[{equals:"qwen/qwen3-next-80b-a3b-instruct"},{equals:"qwen/qwen3-next-80b-a3b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:1.5}},{id:"Qwen/Qwen3-Next-80B-A3B-Thinking",name:"Qwen3-Next-80B-A3B-Thinking",match:{or:[{equals:"qwen/qwen3-next-80b-a3b-thinking"},{equals:"qwen/qwen3-next-80b-a3b-thinking-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:1.5}},{id:"Qwen/Qwen3-VL-235B-A22B-Instruct",name:"Qwen3-VL-235B-A22B-Instruct",match:{or:[{equals:"qwen/qwen3-vl-235b-a22b-instruct"},{equals:"qwen/qwen3-vl-235b-a22b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.3,output_mtok:1.5}},{id:"Qwen/Qwen3-VL-235B-A22B-Thinking",name:"Qwen3-VL-235B-A22B-Thinking",match:{or:[{equals:"qwen/qwen3-vl-235b-a22b-thinking"},{equals:"qwen/qwen3-vl-235b-a22b-thinking-fast"}]},context_window:131072,prices:{input_mtok:.98,output_mtok:3.95}},{id:"Qwen/Qwen3-VL-30B-A3B-Instruct",name:"Qwen3-VL-30B-A3B-Instruct",match:{or:[{equals:"qwen/qwen3-vl-30b-a3b-instruct"},{equals:"qwen/qwen3-vl-30b-a3b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.2,output_mtok:.7}},{id:"Qwen/Qwen3-VL-30B-A3B-Thinking",name:"Qwen3-VL-30B-A3B-Thinking",match:{or:[{equals:"qwen/qwen3-vl-30b-a3b-thinking"},{equals:"qwen/qwen3-vl-30b-a3b-thinking-fast"}]},context_window:131072,prices:{input_mtok:.2,output_mtok:1}},{id:"Qwen/Qwen3-VL-8B-Instruct",name:"Qwen3-VL-8B-Instruct",match:{or:[{equals:"qwen/qwen3-vl-8b-instruct"},{equals:"qwen/qwen3-vl-8b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.08,output_mtok:.5}},{id:"Qwen/Qwen3.5-122B-A10B",name:"Qwen3.5-122B-A10B",match:{or:[{equals:"qwen/qwen3.5-122b-a10b"},{equals:"qwen/qwen3.5-122b-a10b-fast"}]},context_window:262144,prices:{input_mtok:.4,output_mtok:3.2}},{id:"Qwen/Qwen3.5-27B",name:"Qwen3.5-27B",match:{or:[{equals:"qwen/qwen3.5-27b"},{equals:"qwen/qwen3.5-27b-fast"}]},context_window:262144,prices:{input_mtok:.3,output_mtok:2.4}},{id:"Qwen/Qwen3.5-35B-A3B",name:"Qwen3.5-35B-A3B",match:{or:[{equals:"qwen/qwen3.5-35b-a3b"},{equals:"qwen/qwen3.5-35b-a3b-fast"}]},context_window:262144,prices:{input_mtok:.25,output_mtok:2}},{id:"Qwen/Qwen3.5-397B-A17B",name:"Qwen3.5-397B-A17B",match:{or:[{equals:"qwen/qwen3.5-397b-a17b"},{equals:"qwen/qwen3.5-397b-a17b-fast"}]},context_window:262144,prices:{input_mtok:.6,output_mtok:3.6}},{id:"Sao10K/L3-70B-Euryale-v2.1",name:"L3-70B-Euryale-v2.1",match:{or:[{equals:"sao10k/l3-70b-euryale-v2.1"},{equals:"sao10k/l3-70b-euryale-v2.1-fast"}]},context_window:8192,prices:{input_mtok:1.48,output_mtok:1.48}},{id:"Sao10K/L3-8B-Lunaris-v1",name:"L3-8B-Lunaris-v1",match:{or:[{equals:"sao10k/l3-8b-lunaris-v1"},{equals:"sao10k/l3-8b-lunaris-v1-fast"}]},context_window:8192,prices:{input_mtok:.05,output_mtok:.05}},{id:"Sao10K/L3-8B-Stheno-v3.2",name:"L3-8B-Stheno-v3.2",match:{or:[{equals:"sao10k/l3-8b-stheno-v3.2"},{equals:"sao10k/l3-8b-stheno-v3.2-fast"}]},context_window:8192,prices:{input_mtok:.05,output_mtok:.05}},{id:"XiaomiMiMo/MiMo-V2-Flash",name:"MiMo-V2-Flash",match:{or:[{equals:"xiaomimimo/mimo-v2-flash"},{equals:"xiaomimimo/mimo-v2-flash-fast"}]},context_window:262144,prices:{input_mtok:.1,output_mtok:.3}},{id:"alpindale/WizardLM-2-8x22B",name:"WizardLM-2-8x22B",match:{or:[{equals:"alpindale/wizardlm-2-8x22b"},{equals:"alpindale/wizardlm-2-8x22b-fast"}]},context_window:65535,prices:{input_mtok:.62,output_mtok:.62}},{id:"baidu/ERNIE-4.5-21B-A3B-PT",name:"ERNIE-4.5-21B-A3B-PT",match:{or:[{equals:"baidu/ernie-4.5-21b-a3b-pt"},{equals:"baidu/ernie-4.5-21b-a3b-pt-fast"}]},context_window:12e4,prices:{input_mtok:.07,output_mtok:.28}},{id:"baidu/ERNIE-4.5-300B-A47B-Base-PT",name:"ERNIE-4.5-300B-A47B-Base-PT",match:{or:[{equals:"baidu/ernie-4.5-300b-a47b-base-pt"},{equals:"baidu/ernie-4.5-300b-a47b-base-pt-fast"}]},context_window:123e3,prices:{input_mtok:.28,output_mtok:1.1}},{id:"baidu/ERNIE-4.5-VL-28B-A3B-PT",name:"ERNIE-4.5-VL-28B-A3B-PT",match:{or:[{equals:"baidu/ernie-4.5-vl-28b-a3b-pt"},{equals:"baidu/ernie-4.5-vl-28b-a3b-pt-fast"}]},context_window:3e4,prices:{input_mtok:.14,output_mtok:.56}},{id:"baidu/ERNIE-4.5-VL-424B-A47B-Base-PT",name:"ERNIE-4.5-VL-424B-A47B-Base-PT",match:{or:[{equals:"baidu/ernie-4.5-vl-424b-a47b-base-pt"},{equals:"baidu/ernie-4.5-vl-424b-a47b-base-pt-fast"}]},context_window:123e3,prices:{input_mtok:.42,output_mtok:1.25}},{id:"deepseek-ai/DeepSeek-Prover-V2-671B",name:"DeepSeek-Prover-V2-671B",match:{or:[{equals:"deepseek-ai/deepseek-prover-v2-671b"},{equals:"deepseek-ai/deepseek-prover-v2-671b-fast"}]},context_window:16e4,prices:{input_mtok:.7,output_mtok:2.5}},{id:"deepseek-ai/DeepSeek-R1",name:"DeepSeek-R1",match:{or:[{equals:"deepseek-ai/deepseek-r1"},{equals:"deepseek-ai/deepseek-r1-fast"},{equals:"deepseek-ai/deepseek-r1-0528"},{equals:"deepseek-ai/deepseek-r1-0528-fast"}]},context_window:64e3,prices:{input_mtok:.7,output_mtok:2.5}},{id:"deepseek-ai/DeepSeek-R1-Distill-Llama-70B",name:"DeepSeek-R1-Distill-Llama-70B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-llama-70b"},{equals:"deepseek-ai/deepseek-r1-distill-llama-70b-fast"}]},context_window:8192,prices:{input_mtok:.8,output_mtok:.8}},{id:"deepseek-ai/DeepSeek-V3",name:"DeepSeek-V3",match:{or:[{equals:"deepseek-ai/deepseek-v3"},{equals:"deepseek-ai/deepseek-v3-fast"}]},context_window:64e3,prices:{input_mtok:.4,output_mtok:1.3}},{id:"deepseek-ai/DeepSeek-V3-0324",name:"DeepSeek-V3-0324",match:{or:[{equals:"deepseek-ai/deepseek-v3-0324"},{equals:"deepseek-ai/deepseek-v3-0324-fast"}]},context_window:163840,prices:{input_mtok:.27,output_mtok:1.12}},{id:"deepseek-ai/DeepSeek-V3.1",name:"DeepSeek-V3.1",match:{or:[{equals:"deepseek-ai/deepseek-v3.1"},{equals:"deepseek-ai/deepseek-v3.1-fast"},{equals:"deepseek-ai/deepseek-v3.1-terminus"},{equals:"deepseek-ai/deepseek-v3.1-terminus-fast"}]},context_window:131072,prices:{input_mtok:.27,output_mtok:1}},{id:"deepseek-ai/DeepSeek-V3.2",name:"DeepSeek-V3.2",match:{or:[{equals:"deepseek-ai/deepseek-v3.2"},{equals:"deepseek-ai/deepseek-v3.2-fast"}]},context_window:163840,prices:{input_mtok:.269,output_mtok:.4}},{id:"deepseek-ai/DeepSeek-V3.2-Exp",name:"DeepSeek-V3.2-Exp",match:{or:[{equals:"deepseek-ai/deepseek-v3.2-exp"},{equals:"deepseek-ai/deepseek-v3.2-exp-fast"}]},context_window:163840,prices:{input_mtok:.27,output_mtok:.41}},{id:"meta-llama/Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-fast"}]},context_window:16384,prices:{input_mtok:.02,output_mtok:.05}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.135,output_mtok:.4}},{id:"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",name:"Llama-4-Maverick-17B-128E-Instruct-FP8",match:{or:[{equals:"meta-llama/llama-4-maverick-17b-128e-instruct-fp8"},{equals:"meta-llama/llama-4-maverick-17b-128e-instruct-fp8-fast"}]},context_window:1048576,prices:{input_mtok:.27,output_mtok:.85}},{id:"meta-llama/Llama-4-Scout-17B-16E-Instruct",name:"Llama-4-Scout-17B-16E-Instruct",match:{or:[{equals:"meta-llama/llama-4-scout-17b-16e-instruct"},{equals:"meta-llama/llama-4-scout-17b-16e-instruct-fast"}]},context_window:131072,prices:{input_mtok:.18,output_mtok:.59}},{id:"meta-llama/Meta-Llama-3-70B-Instruct",name:"Meta-Llama-3-70B-Instruct",match:{or:[{equals:"meta-llama/meta-llama-3-70b-instruct"},{equals:"meta-llama/meta-llama-3-70b-instruct-fast"}]},context_window:8192,prices:{input_mtok:.51,output_mtok:.74}},{id:"meta-llama/Meta-Llama-3-8B-Instruct",name:"Meta-Llama-3-8B-Instruct",match:{or:[{equals:"meta-llama/meta-llama-3-8b-instruct"},{equals:"meta-llama/meta-llama-3-8b-instruct-fast"}]},context_window:8192,prices:{input_mtok:.04,output_mtok:.04}},{id:"moonshotai/Kimi-K2-Instruct",name:"Kimi-K2-Instruct",match:{or:[{equals:"moonshotai/kimi-k2-instruct"},{equals:"moonshotai/kimi-k2-instruct-fast"}]},context_window:131072,prices:{input_mtok:.57,output_mtok:2.3}},{id:"moonshotai/Kimi-K2-Instruct-0905",name:"Kimi-K2-Instruct-0905",match:{or:[{equals:"moonshotai/kimi-k2-instruct-0905"},{equals:"moonshotai/kimi-k2-instruct-0905-fast"}]},context_window:262144,prices:{input_mtok:.6,output_mtok:2.5}},{id:"moonshotai/Kimi-K2-Thinking",name:"Kimi-K2-Thinking",match:{or:[{equals:"moonshotai/kimi-k2-thinking"},{equals:"moonshotai/kimi-k2-thinking-fast"}]},context_window:262144,prices:{input_mtok:.6,output_mtok:2.5}},{id:"moonshotai/Kimi-K2.5",name:"Kimi-K2.5",match:{or:[{equals:"moonshotai/kimi-k2.5"},{equals:"moonshotai/kimi-k2.5-fast"}]},context_window:262144,prices:{input_mtok:.6,output_mtok:3}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.05,output_mtok:.25}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.04,output_mtok:.15}},{id:"zai-org/AutoGLM-Phone-9B-Multilingual",name:"AutoGLM-Phone-9B-Multilingual",match:{or:[{equals:"zai-org/autoglm-phone-9b-multilingual"},{equals:"zai-org/autoglm-phone-9b-multilingual-fast"}]},context_window:65536,prices:{input_mtok:.035,output_mtok:.138}},{id:"zai-org/GLM-4-32B-0414",name:"GLM-4-32B-0414",match:{or:[{equals:"zai-org/glm-4-32b-0414"},{equals:"zai-org/glm-4-32b-0414-fast"}]},context_window:32e3,prices:{input_mtok:.55,output_mtok:1.66}},{id:"zai-org/GLM-4.5",name:"GLM-4.5",match:{or:[{equals:"zai-org/glm-4.5"},{equals:"zai-org/glm-4.5-fast"}]},context_window:131072,prices:{input_mtok:.6,output_mtok:2.2}},{id:"zai-org/GLM-4.5-Air",name:"GLM-4.5-Air",match:{or:[{equals:"zai-org/glm-4.5-air"},{equals:"zai-org/glm-4.5-air-fast"}]},context_window:131072,prices:{input_mtok:.13,output_mtok:.85}},{id:"zai-org/GLM-4.5V",name:"GLM-4.5V",match:{or:[{equals:"zai-org/glm-4.5v"},{equals:"zai-org/glm-4.5v-fast"}]},context_window:65536,prices:{input_mtok:.6,output_mtok:1.8}},{id:"zai-org/GLM-4.6",name:"GLM-4.6",match:{or:[{equals:"zai-org/glm-4.6"},{equals:"zai-org/glm-4.6-fast"}]},context_window:204800,prices:{input_mtok:.55,output_mtok:2.2}},{id:"zai-org/GLM-4.6V-Flash",name:"GLM-4.6V-Flash",match:{or:[{equals:"zai-org/glm-4.6v-flash"},{equals:"zai-org/glm-4.6v-flash-fast"}]},context_window:131072,prices:{input_mtok:.3,output_mtok:.9}},{id:"zai-org/GLM-4.7",name:"GLM-4.7",match:{or:[{equals:"zai-org/glm-4.7"},{equals:"zai-org/glm-4.7-fast"}]},context_window:204800,prices:{input_mtok:.6,output_mtok:2.2}},{id:"zai-org/GLM-4.7-Flash",name:"GLM-4.7-Flash",match:{or:[{equals:"zai-org/glm-4.7-flash"},{equals:"zai-org/glm-4.7-flash-fast"}]},context_window:2e5,prices:{input_mtok:.07,output_mtok:.4}},{id:"zai-org/GLM-5",name:"GLM-5",match:{or:[{equals:"zai-org/glm-5"},{equals:"zai-org/glm-5-fast"}]},context_window:202800,prices:{input_mtok:1,output_mtok:3.2}}]},{id:"huggingface_nscale",name:"HuggingFace (nscale)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/nscale",provider_match:{and:[{contains:"huggingface"},{contains:"nscale"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"Qwen/QwQ-32B",name:"QwQ-32B",match:{or:[{equals:"qwen/qwq-32b"},{equals:"qwen/qwq-32b-fast"}]},context_window:131072,prices:{input_mtok:.18,output_mtok:.2}},{id:"Qwen/Qwen2.5-Coder-32B-Instruct",name:"Qwen2.5-Coder-32B-Instruct",match:{or:[{equals:"qwen/qwen2.5-coder-32b-instruct"},{equals:"qwen/qwen2.5-coder-32b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.06,output_mtok:.2}},{id:"Qwen/Qwen2.5-Coder-3B-Instruct",name:"Qwen2.5-Coder-3B-Instruct",match:{or:[{equals:"qwen/qwen2.5-coder-3b-instruct"},{equals:"qwen/qwen2.5-coder-3b-instruct-fast"}]},context_window:32768,prices:{input_mtok:.01,output_mtok:.03}},{id:"Qwen/Qwen2.5-Coder-7B-Instruct",name:"Qwen2.5-Coder-7B-Instruct",match:{or:[{equals:"qwen/qwen2.5-coder-7b-instruct"},{equals:"qwen/qwen2.5-coder-7b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.01,output_mtok:.03}},{id:"Qwen/Qwen3-14B",name:"Qwen3-14B",match:{or:[{equals:"qwen/qwen3-14b"},{equals:"qwen/qwen3-14b-fast"}]},context_window:40960,prices:{input_mtok:.07,output_mtok:.2}},{id:"Qwen/Qwen3-235B-A22B",name:"Qwen3-235B-A22B",match:{or:[{equals:"qwen/qwen3-235b-a22b"},{equals:"qwen/qwen3-235b-a22b-fast"},{equals:"qwen/qwen3-235b-a22b-instruct-2507"},{equals:"qwen/qwen3-235b-a22b-instruct-2507-fast"}]},context_window:32e3,prices:{input_mtok:.2,output_mtok:.6}},{id:"Qwen/Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"qwen/qwen3-32b"},{equals:"qwen/qwen3-32b-fast"}]},context_window:40960,prices:{input_mtok:.08,output_mtok:.25}},{id:"Qwen/Qwen3-4B-Instruct-2507",name:"Qwen3-4B-Instruct-2507",match:{or:[{equals:"qwen/qwen3-4b-instruct-2507"},{equals:"qwen/qwen3-4b-instruct-2507-fast"}]},context_window:262144,prices:{input_mtok:.01,output_mtok:.03}},{id:"Qwen/Qwen3-4B-Thinking-2507",name:"Qwen3-4B-Thinking-2507",match:{or:[{equals:"qwen/qwen3-4b-thinking-2507"},{equals:"qwen/qwen3-4b-thinking-2507-fast"}]},context_window:262144,prices:{input_mtok:.01,output_mtok:.03}},{id:"Qwen/Qwen3-8B",name:"Qwen3-8B",match:{or:[{equals:"qwen/qwen3-8b"},{equals:"qwen/qwen3-8b-fast"}]},context_window:40960,prices:{input_mtok:.07,output_mtok:.18}},{id:"deepseek-ai/DeepSeek-R1-Distill-Llama-70B",name:"DeepSeek-R1-Distill-Llama-70B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-llama-70b"},{equals:"deepseek-ai/deepseek-r1-distill-llama-70b-fast"}]},context_window:131072,prices:{input_mtok:.75,output_mtok:.75}},{id:"deepseek-ai/DeepSeek-R1-Distill-Llama-8B",name:"DeepSeek-R1-Distill-Llama-8B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-llama-8b"},{equals:"deepseek-ai/deepseek-r1-distill-llama-8b-fast"}]},context_window:131072,prices:{input_mtok:.05,output_mtok:.05}},{id:"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",name:"DeepSeek-R1-Distill-Qwen-1.5B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-qwen-1.5b"},{equals:"deepseek-ai/deepseek-r1-distill-qwen-1.5b-fast"}]},context_window:131072,prices:{input_mtok:.1,output_mtok:.1}},{id:"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",name:"DeepSeek-R1-Distill-Qwen-32B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-qwen-32b"},{equals:"deepseek-ai/deepseek-r1-distill-qwen-32b-fast"}]},context_window:131072,prices:{input_mtok:.3,output_mtok:.3}},{id:"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",name:"DeepSeek-R1-Distill-Qwen-7B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-qwen-7b"},{equals:"deepseek-ai/deepseek-r1-distill-qwen-7b-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:.15}},{id:"meta-llama/Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.06,output_mtok:.06}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.4,output_mtok:.4}},{id:"meta-llama/Llama-4-Scout-17B-16E-Instruct",name:"Llama-4-Scout-17B-16E-Instruct",match:{or:[{equals:"meta-llama/llama-4-scout-17b-16e-instruct"},{equals:"meta-llama/llama-4-scout-17b-16e-instruct-fast"}]},context_window:89e4,prices:{input_mtok:.09,output_mtok:.29}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.1,output_mtok:.4}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.05,output_mtok:.2}}]},{id:"huggingface_ovhcloud",name:"HuggingFace (ovhcloud)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/ovhcloud",provider_match:{and:[{contains:"huggingface"},{contains:"ovhcloud"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"Qwen/Qwen2.5-VL-72B-Instruct",name:"Qwen2.5-VL-72B-Instruct",match:{or:[{equals:"qwen/qwen2.5-vl-72b-instruct"},{equals:"qwen/qwen2.5-vl-72b-instruct-fast"}]},context_window:32768,prices:{input_mtok:1.01,output_mtok:1.01}},{id:"Qwen/Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"qwen/qwen3-32b"},{equals:"qwen/qwen3-32b-fast"}]},context_window:32768,prices:{input_mtok:.09,output_mtok:.25}},{id:"Qwen/Qwen3-Coder-30B-A3B-Instruct",name:"Qwen3-Coder-30B-A3B-Instruct",match:{or:[{equals:"qwen/qwen3-coder-30b-a3b-instruct"},{equals:"qwen/qwen3-coder-30b-a3b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.07,output_mtok:.26}},{id:"meta-llama/Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.11,output_mtok:.11}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.74,output_mtok:.74}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.09,output_mtok:.47}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.05,output_mtok:.18}}]},{id:"huggingface_publicai",name:"HuggingFace (publicai)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/publicai",provider_match:{and:[{contains:"huggingface"},{contains:"publicai"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"aisingapore/Gemma-SEA-LION-v4-27B-IT",name:"Gemma-SEA-LION-v4-27B-IT",match:{or:[{equals:"aisingapore/gemma-sea-lion-v4-27b-it"},{equals:"aisingapore/gemma-sea-lion-v4-27b-it-fast"}]},prices:{input_mtok:.2,output_mtok:.4}},{id:"aisingapore/Qwen-SEA-LION-v4-32B-IT",name:"Qwen-SEA-LION-v4-32B-IT",match:{or:[{equals:"aisingapore/qwen-sea-lion-v4-32b-it"},{equals:"aisingapore/qwen-sea-lion-v4-32b-it-fast"}]},prices:{input_mtok:.25,output_mtok:.5}},{id:"allenai/Olmo-3-7B-Instruct",name:"Olmo-3-7B-Instruct",match:{or:[{equals:"allenai/olmo-3-7b-instruct"},{equals:"allenai/olmo-3-7b-instruct-fast"}]},prices:{input_mtok:.1,output_mtok:.2}},{id:"allenai/Olmo-3.1-32B-Instruct",name:"Olmo-3.1-32B-Instruct",match:{or:[{equals:"allenai/olmo-3.1-32b-instruct"},{equals:"allenai/olmo-3.1-32b-instruct-fast"}]},prices:{input_mtok:.2,output_mtok:.6}},{id:"dicta-il/DictaLM-3.0-24B-Thinking",name:"DictaLM-3.0-24B-Thinking",match:{or:[{equals:"dicta-il/dictalm-3.0-24b-thinking"},{equals:"dicta-il/dictalm-3.0-24b-thinking-fast"}]},prices:{input_mtok:.2,output_mtok:.4}},{id:"swiss-ai/Apertus-70B-Instruct-2509",name:"Apertus-70B-Instruct-2509",match:{or:[{equals:"swiss-ai/apertus-70b-instruct-2509"},{equals:"swiss-ai/apertus-70b-instruct-2509-fast"}]},prices:{input_mtok:.82,output_mtok:2.92}},{id:"swiss-ai/Apertus-8B-Instruct-2509",name:"Apertus-8B-Instruct-2509",match:{or:[{equals:"swiss-ai/apertus-8b-instruct-2509"},{equals:"swiss-ai/apertus-8b-instruct-2509-fast"}]},prices:{input_mtok:.1,output_mtok:.2}},{id:"utter-project/EuroLLM-22B-Instruct-2512",name:"EuroLLM-22B-Instruct-2512",match:{or:[{equals:"utter-project/eurollm-22b-instruct-2512"},{equals:"utter-project/eurollm-22b-instruct-2512-fast"}]},prices:{input_mtok:.1,output_mtok:.2}}]},{id:"huggingface_sambanova",name:"HuggingFace (sambanova)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/sambanova",provider_match:{and:[{contains:"huggingface"},{contains:"sambanova"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"Qwen/Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"qwen/qwen3-32b"},{equals:"qwen/qwen3-32b-fast"}]},context_window:32768,prices:{input_mtok:.4,output_mtok:.8}},{id:"deepseek-ai/DeepSeek-R1-0528",name:"DeepSeek-R1-0528",match:{or:[{equals:"deepseek-ai/deepseek-r1-0528"},{equals:"deepseek-ai/deepseek-r1-0528-fast"}]},context_window:131072,prices:{input_mtok:5,output_mtok:7}},{id:"deepseek-ai/DeepSeek-R1-Distill-Llama-70B",name:"DeepSeek-R1-Distill-Llama-70B",match:{or:[{equals:"deepseek-ai/deepseek-r1-distill-llama-70b"},{equals:"deepseek-ai/deepseek-r1-distill-llama-70b-fast"}]},context_window:131072,prices:{input_mtok:.7,output_mtok:1.4}},{id:"deepseek-ai/DeepSeek-V3-0324",name:"DeepSeek-V3-0324",match:{or:[{equals:"deepseek-ai/deepseek-v3-0324"},{equals:"deepseek-ai/deepseek-v3-0324-fast"}]},context_window:131072,prices:{input_mtok:3,output_mtok:4.5}},{id:"meta-llama/Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-fast"}]},context_window:16384,prices:{input_mtok:.1,output_mtok:.2}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.6,output_mtok:1.2}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.22,output_mtok:.59}},{id:"tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4",name:"Llama-3.3-Swallow-70B-Instruct-v0.4",match:{or:[{equals:"tokyotech-llm/llama-3.3-swallow-70b-instruct-v0.4"},{equals:"tokyotech-llm/llama-3.3-swallow-70b-instruct-v0.4-fast"}]},context_window:131072,prices:{input_mtok:.6,output_mtok:1.2}}]},{id:"huggingface_together",name:"HuggingFace (together)",pricing_urls:["https://router.huggingface.co/v1/models","https://huggingface.co/inference/models"],api_pattern:"https://router\\.huggingface\\.co/together",provider_match:{and:[{contains:"huggingface"},{contains:"together"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"EssentialAI/rnj-1-instruct",name:"rnj-1-instruct",match:{or:[{equals:"essentialai/rnj-1-instruct"},{equals:"essentialai/rnj-1-instruct-fast"}]},context_window:32768,prices:{input_mtok:.15,output_mtok:.15}},{id:"Qwen/Qwen2.5-7B-Instruct",name:"Qwen2.5-7B-Instruct",match:{or:[{equals:"qwen/qwen2.5-7b-instruct"},{equals:"qwen/qwen2.5-7b-instruct-fast"}]},context_window:32768,prices:{input_mtok:.3,output_mtok:.3}},{id:"Qwen/Qwen3-235B-A22B-Instruct-2507",name:"Qwen3-235B-A22B-Instruct-2507",match:{or:[{equals:"qwen/qwen3-235b-a22b-instruct-2507"},{equals:"qwen/qwen3-235b-a22b-instruct-2507-fast"}]},context_window:262144,prices:{input_mtok:.2,output_mtok:.6}},{id:"Qwen/Qwen3-Coder-480B-A35B-Instruct",name:"Qwen3-Coder-480B-A35B-Instruct",match:{or:[{equals:"qwen/qwen3-coder-480b-a35b-instruct"},{equals:"qwen/qwen3-coder-480b-a35b-instruct-fast"},{equals:"qwen/qwen3-coder-480b-a35b-instruct-fp8"},{equals:"qwen/qwen3-coder-480b-a35b-instruct-fp8-fast"}]},context_window:262144,prices:{input_mtok:2,output_mtok:2}},{id:"Qwen/Qwen3-Coder-Next-FP8",name:"Qwen3-Coder-Next-FP8",match:{or:[{equals:"qwen/qwen3-coder-next-fp8"},{equals:"qwen/qwen3-coder-next-fp8-fast"}]},context_window:262144,prices:{input_mtok:.5,output_mtok:1.2}},{id:"Qwen/Qwen3-Next-80B-A3B-Instruct",name:"Qwen3-Next-80B-A3B-Instruct",match:{or:[{equals:"qwen/qwen3-next-80b-a3b-instruct"},{equals:"qwen/qwen3-next-80b-a3b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.15,output_mtok:1.5}},{id:"Qwen/Qwen3-VL-8B-Instruct",name:"Qwen3-VL-8B-Instruct",match:{or:[{equals:"qwen/qwen3-vl-8b-instruct"},{equals:"qwen/qwen3-vl-8b-instruct-fast"}]},context_window:262144,prices:{input_mtok:.18000000000000002,output_mtok:.68}},{id:"Qwen/Qwen3.5-397B-A17B",name:"Qwen3.5-397B-A17B",match:{or:[{equals:"qwen/qwen3.5-397b-a17b"},{equals:"qwen/qwen3.5-397b-a17b-fast"}]},context_window:262144,prices:{input_mtok:.6,output_mtok:3.6}},{id:"Qwen/Qwen3.5-9B",name:"Qwen3.5-9B",match:{or:[{equals:"qwen/qwen3.5-9b"},{equals:"qwen/qwen3.5-9b-fast"}]},context_window:262144,prices:{input_mtok:.1,output_mtok:.15}},{id:"ServiceNow-AI/Apriel-1.6-15b-Thinker",name:"Apriel-1.6-15b-Thinker",match:{or:[{equals:"servicenow-ai/apriel-1.6-15b-thinker"},{equals:"servicenow-ai/apriel-1.6-15b-thinker-fast"}]},context_window:131072,prices:{}},{id:"deepcogito/cogito-671b-v2.1",name:"cogito-671b-v2.1",match:{or:[{equals:"deepcogito/cogito-671b-v2.1"},{equals:"deepcogito/cogito-671b-v2.1-fast"},{equals:"deepcogito/cogito-671b-v2.1-fp8"},{equals:"deepcogito/cogito-671b-v2.1-fp8-fast"}]},context_window:163840,prices:{input_mtok:1.25,output_mtok:1.25}},{id:"deepseek-ai/DeepSeek-R1",name:"DeepSeek-R1",match:{or:[{equals:"deepseek-ai/deepseek-r1"},{equals:"deepseek-ai/deepseek-r1-fast"},{equals:"deepseek-ai/deepseek-r1-0528"},{equals:"deepseek-ai/deepseek-r1-0528-fast"}]},context_window:163840,prices:{input_mtok:3,output_mtok:7}},{id:"deepseek-ai/DeepSeek-V3",name:"DeepSeek-V3",match:{or:[{equals:"deepseek-ai/deepseek-v3"},{equals:"deepseek-ai/deepseek-v3-fast"},{equals:"deepseek-ai/deepseek-v3-0324"},{equals:"deepseek-ai/deepseek-v3-0324-fast"}]},context_window:131072,prices:{input_mtok:1.25,output_mtok:1.25}},{id:"deepseek-ai/DeepSeek-V3.1",name:"DeepSeek-V3.1",match:{or:[{equals:"deepseek-ai/deepseek-v3.1"},{equals:"deepseek-ai/deepseek-v3.1-fast"}]},context_window:131072,prices:{input_mtok:.6,output_mtok:1.7}},{id:"google/gemma-3n-E4B-it",name:"gemma-3n-E4B-it",match:{or:[{equals:"google/gemma-3n-e4b-it"},{equals:"google/gemma-3n-e4b-it-fast"}]},context_window:32768,prices:{input_mtok:.02,output_mtok:.04}},{id:"meta-llama/Llama-3.3-70B-Instruct",name:"Llama-3.3-70B-Instruct",match:{or:[{equals:"meta-llama/llama-3.3-70b-instruct"},{equals:"meta-llama/llama-3.3-70b-instruct-fast"}]},context_window:131072,prices:{input_mtok:.88,output_mtok:.88}},{id:"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",name:"Llama-4-Maverick-17B-128E-Instruct-FP8",match:{or:[{equals:"meta-llama/llama-4-maverick-17b-128e-instruct-fp8"},{equals:"meta-llama/llama-4-maverick-17b-128e-instruct-fp8-fast"}]},context_window:1048576,prices:{input_mtok:.27,output_mtok:.85}},{id:"moonshotai/Kimi-K2.5",name:"Kimi-K2.5",match:{or:[{equals:"moonshotai/kimi-k2.5"},{equals:"moonshotai/kimi-k2.5-fast"}]},context_window:262144,prices:{input_mtok:.5,output_mtok:2.8}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b-fast"}]},context_window:131072,prices:{input_mtok:.15,output_mtok:.6}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{or:[{equals:"openai/gpt-oss-20b"},{equals:"openai/gpt-oss-20b-fast"}]},context_window:131072,prices:{input_mtok:.05,output_mtok:.2}},{id:"zai-org/GLM-4.5-Air-FP8",name:"GLM-4.5-Air-FP8",match:{or:[{equals:"zai-org/glm-4.5-air-fp8"},{equals:"zai-org/glm-4.5-air-fp8-fast"}]},context_window:131072,prices:{input_mtok:.2,output_mtok:1.1}},{id:"zai-org/GLM-4.6",name:"GLM-4.6",match:{or:[{equals:"zai-org/glm-4.6"},{equals:"zai-org/glm-4.6-fast"}]},context_window:202752,prices:{input_mtok:.6,output_mtok:2.2}},{id:"zai-org/GLM-4.7-FP8",name:"GLM-4.7-FP8",match:{or:[{equals:"zai-org/glm-4.7-fp8"},{equals:"zai-org/glm-4.7-fp8-fast"}]},context_window:202752,prices:{input_mtok:.45,output_mtok:2}},{id:"zai-org/GLM-5",name:"GLM-5",match:{or:[{equals:"zai-org/glm-5"},{equals:"zai-org/glm-5-fast"}]},context_window:202752,prices:{input_mtok:1,output_mtok:3.2}}]},{id:"minimax",name:"MiniMax",pricing_urls:["https://platform.minimax.io/docs/guides/pricing-paygo"],api_pattern:"https://api\\.minimax(i)?\\.(?:com|io)",price_comments:"Prices sourced from MiniMax international platform USD pricing (platform.minimax.io, May 2026). M2.1, M2.1-highspeed, and M2 are legacy models; prices inferred from CNY pricing at the equivalent 7.00 CNY/USD rate used by the international platform for current models.",model_match:{or:[{starts_with:"MiniMax-M"},{starts_with:"minimax-m"},{equals:"minimax-01"},{equals:"M2-her"},{equals:"m2-her"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"M2-her",name:"MiniMax M2-her",description:"MiniMax M2-her, a text dialogue model optimized for role-playing and multi-turn conversations. 64,000 token context window. No cache support.",match:{or:[{equals:"M2-her"},{equals:"m2-her"}]},context_window:64e3,prices:{input_mtok:.3,output_mtok:1.2}},{id:"MiniMax-M2",name:"MiniMax M2",description:"MiniMax M2 (legacy), a multimodal language model with 204,800 token context window. Supports agentic capabilities and advanced reasoning.",match:{or:[{equals:"MiniMax-M2"},{equals:"minimax-m2"},{equals:"MiniMax-M2.1"},{equals:"minimax-m2.1"},{equals:"MiniMax-M2.5"},{equals:"minimax-m2.5"}]},context_window:204800,prices:{input_mtok:.3,cache_write_mtok:.375,cache_read_mtok:.03,output_mtok:1.2}},{id:"MiniMax-M2.1-highspeed",name:"MiniMax M2.1 Highspeed",description:"MiniMax M2.1 highspeed variant (legacy) with higher throughput.",match:{or:[{contains:"M2.1-highspeed"},{contains:"m2.1-highspeed"}]},context_window:204800,prices:{input_mtok:.6,cache_write_mtok:.375,cache_read_mtok:.03,output_mtok:2.4}},{id:"MiniMax-M2.5-highspeed",name:"MiniMax M2.5 Highspeed",description:"MiniMax M2.5 highspeed variant with higher throughput.",match:{or:[{contains:"M2.5-highspeed"},{contains:"m2.5-highspeed"}]},context_window:204800,prices:{input_mtok:.6,cache_write_mtok:.375,cache_read_mtok:.03,output_mtok:2.4}},{id:"MiniMax-M2.7",name:"MiniMax M2.7",description:"MiniMax M2.7, a multimodal language model with 204,800 token context window. Achieves top performance in real-world engineering, office productivity, and character-rich interaction.",match:{or:[{equals:"MiniMax-M2.7"},{equals:"minimax-m2.7"}]},context_window:204800,prices:{input_mtok:.3,cache_write_mtok:.375,cache_read_mtok:.06,output_mtok:1.2}},{id:"MiniMax-M2.7-highspeed",name:"MiniMax M2.7 Highspeed",description:"MiniMax M2.7 highspeed variant with higher throughput.",match:{or:[{contains:"M2.7-highspeed"},{contains:"m2.7-highspeed"}]},context_window:204800,prices:{input_mtok:.6,cache_write_mtok:.375,cache_read_mtok:.06,output_mtok:2.4}},{id:"minimax-01",name:"MiniMax-01",description:"MiniMax-01 combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding.",match:{equals:"minimax-01"},price_comments:"Imported from OpenRouter pricing; verify against MiniMax pricing when native API pricing is published.",prices:{input_mtok:.2,output_mtok:1.1}},{id:"minimax-m1",name:"MiniMax M1",description:'MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing efficient long-context processing.',match:{equals:"minimax-m1"},price_comments:"Imported from OpenRouter pricing; verify against MiniMax pricing when native API pricing is published.",prices:{input_mtok:.4,output_mtok:2.2}},{id:"minimax-m3",name:"MiniMax M3",description:"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and long-horizon agentic work.",match:{equals:"minimax-m3"},price_comments:"Imported from OpenRouter pricing; verify against MiniMax pricing when native API pricing is published.",prices:{input_mtok:.3,cache_read_mtok:.06,output_mtok:1.2}}]},{id:"mistral",name:"Mistral",pricing_urls:["https://mistral.ai/pricing#api-pricing"],api_pattern:"https://api\\.mistral\\.ai",model_match:{regex:"(?:mi|code|dev|magi|mini)stral"},provider_match:{starts_with:"mistral"},extractors:[{api_flavor:"default",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"codestral",name:"Codestral",description:"Mistral's cutting-edge language model for coding. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.",match:{or:[{equals:"codestral-latest"},{equals:"codestral-2501"}]},prices:{input_mtok:.3,output_mtok:.9}},{id:"codestral-2508",name:"Codestral 2508",description:"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.",match:{equals:"codestral-2508"},prices:{input_mtok:.3,cache_read_mtok:.03,output_mtok:.9}},{id:"devstral-2512",name:"Devstral 2 2512",description:"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.",match:{equals:"devstral-2512"},prices:{input_mtok:.4,cache_read_mtok:.04,output_mtok:2}},{id:"devstral-small",name:"Devstral Small",description:"Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%).",match:{equals:"devstral-small"},prices:{input_mtok:.06,output_mtok:.12}},{id:"devstral-small:free",name:"Devstral Small (free)",description:"Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%).",match:{equals:"devstral-small:free"},prices:{}},{id:"magistral-medium",name:"Magistral Medium",description:"Magistral is Mistral's first reasoning model. It is ideal for general purpose use requiring longer thought processing and better accuracy than with non-reasoning LLMs. From legal research and financial forecasting to software development and creative storytelling — this model solves multi-step challenges where transparency and precision are critical.",match:{or:[{starts_with:"magistral-medium"}]},prices:{input_mtok:2,output_mtok:5}},{id:"magistral-small",name:"Magistral Small",description:"Magistral Small is a 24B parameter instruction-tuned model based on Mistral-Small-3.1 (2503), enhanced through supervised fine-tuning on traces from Magistral Medium and further refined via reinforcement learning. It is optimized for reasoning and supports a wide multilingual range, including over 20 languages.",match:{starts_with:"magistral-small-"},prices:{input_mtok:.5,output_mtok:1.5}},{id:"ministral-14b-2512",name:"Ministral 3 14B 2512",description:"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart.",match:{equals:"ministral-14b-2512"},prices:{input_mtok:.2,cache_read_mtok:.02,output_mtok:.2}},{id:"ministral-3b",name:"Ministral 3B",description:"Ministral 3B is a 3B parameter model optimized for on-device and edge computing. It excels in knowledge, commonsense reasoning, and function-calling, outperforming larger models like Mistral 7B on most benchmarks. Supporting up to 128k context length, it's ideal for orchestrating agentic workflows and specialist tasks with efficient inference.",match:{equals:"ministral-3b"},prices:{input_mtok:.04,output_mtok:.04}},{id:"ministral-3b-2512",name:"Ministral 3 3B 2512",description:"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.",match:{equals:"ministral-3b-2512"},prices:{input_mtok:.1,cache_read_mtok:.01,output_mtok:.1}},{id:"ministral-8b",name:"Ministral 8B 24.10",description:"Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect for low-latency, privacy-first applications.",match:{starts_with:"ministral-8b"},prices:{input_mtok:.1,output_mtok:1}},{id:"mistral-7b",name:"Mistral 7B",match:{or:[{equals:"mistral-7b"},{equals:"open-mistral-7b"}]},prices:{input_mtok:.25,output_mtok:.25}},{id:"mistral-embed",match:{equals:"mistral-embed"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistral-large",name:"Mistral Large",description:"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here.",match:{or:[{equals:"mistral-large"},{equals:"mistral-large-latest"},{equals:"mistral-large-2407"},{equals:"mistral-large-2411"}]},prices:{input_mtok:2,output_mtok:6}},{id:"mistral-large-2512",name:"Mistral Large 3 2512",description:"Mistral Large 3 2512 is Mistral's most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.",match:{equals:"mistral-large-2512"},prices:{input_mtok:.5,cache_read_mtok:.05,output_mtok:1.5}},{id:"mistral-medium-3",name:"Mistral Medium 3",description:"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.",match:{starts_with:"mistral-medium"},prices:{input_mtok:.4,output_mtok:2}},{id:"mistral-nemo",name:"Mistral NeMo",description:"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.",match:{or:[{equals:"mistral-nemo"},{equals:"open-mistral-nemo"}]},prices:{input_mtok:.15,output_mtok:.15}},{id:"mistral-nemo:free",name:"Mistral Nemo (free)",description:"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.",match:{equals:"mistral-nemo:free"},prices:{}},{id:"mistral-saba",name:"Mistral Saba",description:"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional datasets, it supports multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. This makes it a versatile option for a range of regional and multilingual applications. Read more at the blog post here",match:{or:[{equals:"mistral-saba"},{equals:"mistral-saba-latest"}]},prices:{input_mtok:.2,output_mtok:.6}},{id:"mistral-small-24b-instruct-2501",name:"Mistral Small 3",description:"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment.",match:{equals:"mistral-small-24b-instruct-2501"},price_comments:"Can't find pricing on this model, so just trusting open router",prices:{input_mtok:.05,output_mtok:.08}},{id:"mistral-small-24b-instruct-2501:free",name:"Mistral Small 3 (free)",description:"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment.",match:{equals:"mistral-small-24b-instruct-2501:free"},prices:{}},{id:"mistral-small-2603",name:"Mistral Small 4",description:"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system.",match:{equals:"mistral-small-2603"},prices:{input_mtok:.15,cache_read_mtok:.015,output_mtok:.6}},{id:"mistral-small-3.1-24b-instruct",name:"Mistral Small 3.1 24B",description:"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities.",match:{equals:"mistral-small-3.1-24b-instruct"},price_comments:"Imported from OpenRouter pricing; verify against Mistral pricing when native API pricing is published.",prices:{input_mtok:.351,output_mtok:.555}},{id:"mistral-small-3.2-24b-instruct",name:"Mistral Small 3.2 24B",description:"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling.",match:{equals:"mistral-small-3.2-24b-instruct"},price_comments:"Imported from OpenRouter pricing; verify against Mistral pricing when native API pricing is published.",prices:{input_mtok:.075,output_mtok:.2}},{id:"mistral-small-latest",name:"Mistral Small 3.2",description:"SOTA. Multimodal. Multilingual. Apache 2.0.",match:{equals:"mistral-small-latest"},prices:{input_mtok:.1,output_mtok:.3}},{id:"mistral-tiny",name:"Mistral Tiny",description:"Note: This model is being deprecated. Recommended replacement is the newer Ministral 8B",match:{equals:"mistral-tiny"},prices:{input_mtok:.25,output_mtok:.25},deprecated:!0},{id:"mixtral-8x22b-instruct",name:"Mixtral 8x22B Instruct",description:`Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include:
8
8
  - strong math, coding, and reasoning
9
9
  - large context length (64k)
10
- - fluency in English, French, Italian, German, and Spanish`,match:{equals:"mixtral-8x22b-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"mixtral-8x7b",name:"Mixtral 8x7B",match:{or:[{starts_with:"mixtral-8x7b"},{equals:"open-mixtral-8x7b"}]},prices:{input_mtok:.7,output_mtok:.7}},{id:"pixtral-12b",name:"Pixtral 12B",description:"The first multi-modal, text+image-to-text model from Mistral AI. Its weights were launched via torrent: https://x.com/mistralai/status/1833758285167722836.",match:{or:[{equals:"pixtral-12b"},{equals:"pixtral-12b-latest"}]},prices:{input_mtok:.15,output_mtok:.15}},{id:"pixtral-large",name:"Pixtral Large 2411",description:"Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of Mistral Large 2. The model is able to understand documents, charts and natural images.",match:{or:[{equals:"pixtral-large-latest"},{equals:"pixtral-large-2411"}]},prices:{input_mtok:2,output_mtok:6}}]},{id:"moonshotai",name:"MoonshotAi",pricing_urls:["https://platform.moonshot.ai/docs/pricing/chat#product-pricing"],api_pattern:"https://api\\.moonshot\\.",model_match:{or:[{starts_with:"kimi"},{starts_with:"moonshot"}]},provider_match:{contains:"moonshot"},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"kimi-k2-0711-preview",name:"Kimi K2 0711 Preview",description:"MoE foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters.",match:{equals:"kimi-k2-0711-preview"},context_window:131072,prices:{input_mtok:.6,cache_read_mtok:.15,output_mtok:2.5}},{id:"kimi-k2-0905-preview",name:"Kimi K2 0905 Preview",description:"Based on kimi-k2-0711-preview, with enhanced agentic coding abilities, improved frontend code quality and practicality, and better context understanding. MoE foundation model with 1 trillion total parameters and 32 billion activated parameters.",match:{equals:"kimi-k2-0905-preview"},context_window:262144,prices:{input_mtok:.6,cache_read_mtok:.15,output_mtok:2.5}},{id:"kimi-k2-thinking",name:"Kimi K2 Thinking",description:"A thinking model with general agentic and reasoning capabilities, specializing in deep reasoning tasks.",match:{equals:"kimi-k2-thinking"},context_window:262144,prices:{input_mtok:.6,cache_read_mtok:.15,output_mtok:2.5}},{id:"kimi-k2-thinking-turbo",name:"Kimi K2 Thinking Turbo",description:"High-speed version of kimi-k2-thinking, suitable for scenarios requiring both deep reasoning and extremely fast responses.",match:{equals:"kimi-k2-thinking-turbo"},context_window:262144,prices:{input_mtok:1.15,cache_read_mtok:.15,output_mtok:8}},{id:"kimi-k2-turbo-preview",name:"Kimi K2 Turbo Preview",description:"High-speed version of kimi-k2, always aligned with the latest kimi-k2. Same model parameters as kimi-k2, output speed up to 60 tokens/sec (max 100 tokens/sec).",match:{starts_with:"kimi-k2-turbo"},context_window:262144,prices:{input_mtok:1.15,cache_read_mtok:.15,output_mtok:8}},{id:"kimi-k2.5",name:"Kimi K2.5",description:"Kimi's most versatile model featuring a native multimodal architecture that supports both visual and text input, thinking and non-thinking modes, and dialogue and agent tasks. Supports automatic context caching, ToolCalls, JSON Mode, Partial Mode, and internet search.",match:{starts_with:"kimi-k2.5"},context_window:262144,prices:{input_mtok:.6,cache_read_mtok:.1,output_mtok:3}},{id:"kimi-k2.6",name:"Kimi K2.6",description:"Kimi's most capable model with enhanced long-context coding stability, improved instruction compliance and self-correction capabilities. Native multimodal architecture supporting text, image, and video input, thinking and non-thinking modes, and agent tasks. Supports automatic context caching, ToolCalls, JSON Mode, Partial Mode, and internet search.",match:{starts_with:"kimi-k2.6"},context_window:262144,prices:{input_mtok:.95,cache_read_mtok:.16,output_mtok:4}},{id:"moonshot-v1-128k",name:"Moonshot V1 128K",match:{or:[{equals:"moonshot-v1-128k"},{equals:"moonshot-v1-128k-vision-preview"}]},context_window:131072,prices:{input_mtok:2,output_mtok:5}},{id:"moonshot-v1-32k",name:"Moonshot V1 32K",match:{or:[{equals:"moonshot-v1-32k"},{equals:"moonshot-v1-32k-vision-preview"}]},context_window:32768,prices:{input_mtok:1,output_mtok:3}},{id:"moonshot-v1-8k",name:"Moonshot V1 8K",match:{or:[{equals:"moonshot-v1-8k"},{equals:"moonshot-v1-8k-vision-preview"}]},context_window:8192,prices:{input_mtok:.2,output_mtok:2}}]},{id:"novita",name:"Novita",pricing_urls:["https://novita.ai/pricing"],api_pattern:"https://api\\.novita\\.ai",models:[{id:"Sao10K/L3-8B-Stheno-v3.2",match:{equals:"Sao10K/L3-8B-Stheno-v3.2"},prices:{input_mtok:.05,output_mtok:.05}},{id:"cognitivecomputations/dolphin-mixtral-8x22b",match:{equals:"cognitivecomputations/dolphin-mixtral-8x22b"},prices:{input_mtok:.9,output_mtok:.9}},{id:"deepseek/deepseek-r1",match:{equals:"deepseek/deepseek-r1"},prices:{input_mtok:4,output_mtok:4}},{id:"deepseek/deepseek-r1-distill-llama-70b",match:{equals:"deepseek/deepseek-r1-distill-llama-70b"},prices:{input_mtok:.8,output_mtok:.8}},{id:"deepseek/deepseek-r1-distill-llama-8b",match:{equals:"deepseek/deepseek-r1-distill-llama-8b"},prices:{input_mtok:.04,output_mtok:.04}},{id:"deepseek/deepseek-r1-distill-qwen-14b",match:{equals:"deepseek/deepseek-r1-distill-qwen-14b"},prices:{input_mtok:.15,output_mtok:.15}},{id:"deepseek/deepseek-r1-distill-qwen-32b",match:{equals:"deepseek/deepseek-r1-distill-qwen-32b"},prices:{input_mtok:.3,output_mtok:.3}},{id:"deepseek/deepseek_v3",match:{equals:"deepseek/deepseek_v3"},prices:{input_mtok:.89,output_mtok:.89}},{id:"google/gemma-2-9b-it",match:{equals:"google/gemma-2-9b-it"},prices:{input_mtok:.08,output_mtok:.08}},{id:"gryphe/mythomax-l2-13b",match:{equals:"gryphe/mythomax-l2-13b"},prices:{input_mtok:.09,output_mtok:.09}},{id:"jondurbin/airoboros-l2-70b",match:{equals:"jondurbin/airoboros-l2-70b"},prices:{input_mtok:.5,output_mtok:.5}},{id:"meta-llama/llama-3-70b-instruct",match:{equals:"meta-llama/llama-3-70b-instruct"},prices:{input_mtok:.51,output_mtok:.74}},{id:"meta-llama/llama-3-8b-instruct",match:{equals:"meta-llama/llama-3-8b-instruct"},prices:{input_mtok:.04,output_mtok:.04}},{id:"meta-llama/llama-3.1-70b-instruct",match:{equals:"meta-llama/llama-3.1-70b-instruct"},prices:{input_mtok:.34,output_mtok:.39}},{id:"meta-llama/llama-3.1-8b-instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-max"}]},prices:{input_mtok:.05,output_mtok:.05}},{id:"meta-llama/llama-3.1-8b-instruct-bf16",match:{equals:"meta-llama/llama-3.1-8b-instruct-bf16"},prices:{input_mtok:.06,output_mtok:.06}},{id:"meta-llama/llama-3.2-11b-vision-instruct",match:{equals:"meta-llama/llama-3.2-11b-vision-instruct"},prices:{input_mtok:.06,output_mtok:.06}},{id:"meta-llama/llama-3.2-1b-instruct",match:{equals:"meta-llama/llama-3.2-1b-instruct"},prices:{input_mtok:.02,output_mtok:.02}},{id:"meta-llama/llama-3.2-3b-instruct",match:{equals:"meta-llama/llama-3.2-3b-instruct"},prices:{input_mtok:.03,output_mtok:.05}},{id:"meta-llama/llama-3.3-70b-instruct",match:{equals:"meta-llama/llama-3.3-70b-instruct"},prices:{input_mtok:.39,output_mtok:.39}},{id:"microsoft/wizardlm-2-8x22b",match:{equals:"microsoft/wizardlm-2-8x22b"},prices:{input_mtok:.62,output_mtok:.62}},{id:"mistralai/mistral-7b-instruct",match:{equals:"mistralai/mistral-7b-instruct"},prices:{input_mtok:.059,output_mtok:.059}},{id:"mistralai/mistral-nemo",match:{equals:"mistralai/mistral-nemo"},prices:{input_mtok:.17,output_mtok:.17}},{id:"nousresearch/hermes-2-pro-llama-3-8b",match:{equals:"nousresearch/hermes-2-pro-llama-3-8b"},prices:{input_mtok:.14,output_mtok:.14}},{id:"nousresearch/nous-hermes-llama2-13b",match:{equals:"nousresearch/nous-hermes-llama2-13b"},prices:{input_mtok:.17,output_mtok:.17}},{id:"openchat/openchat-7b",match:{equals:"openchat/openchat-7b"},prices:{input_mtok:.06,output_mtok:.06}},{id:"qwen/qwen-2-7b-instruct",match:{equals:"qwen/qwen-2-7b-instruct"},prices:{input_mtok:.054,output_mtok:.054}},{id:"qwen/qwen-2-vl-72b-instruct",match:{equals:"qwen/qwen-2-vl-72b-instruct"},prices:{input_mtok:.45,output_mtok:.45}},{id:"qwen/qwen-2.5-72b-instruct",match:{equals:"qwen/qwen-2.5-72b-instruct"},prices:{input_mtok:.38,output_mtok:.4}},{id:"sao10k/l3-70b-euryale-v2.1",match:{equals:"sao10k/l3-70b-euryale-v2.1"},prices:{input_mtok:1.48,output_mtok:1.48}},{id:"sao10k/l3-8b-lunaris",match:{equals:"sao10k/l3-8b-lunaris"},prices:{input_mtok:.05,output_mtok:.05}},{id:"sao10k/l31-70b-euryale-v2.2",match:{equals:"sao10k/l31-70b-euryale-v2.2"},prices:{input_mtok:1.48,output_mtok:1.48}},{id:"sophosympatheia/midnight-rose-70b",match:{equals:"sophosympatheia/midnight-rose-70b"},prices:{input_mtok:.8,output_mtok:.8}},{id:"teknium/openhermes-2.5-mistral-7b",match:{equals:"teknium/openhermes-2.5-mistral-7b"},prices:{input_mtok:.17,output_mtok:.17}}]},{id:"openai",name:"OpenAI",pricing_urls:["https://platform.openai.com/docs/pricing","https://openai.com/api/pricing/","https://platform.openai.com/docs/models","https://help.openai.com/en/articles/7127956-how-much-does-gpt-4-cost"],api_pattern:"https://api\\.openai\\.com",model_match:{or:[{starts_with:"gpt-"},{regex:"^o[134]"}]},provider_match:{contains:"openai"},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"responses",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:["input_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"embeddings",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0}]}],models:[{id:"ada",match:{or:[{equals:"ada"},{equals:"text-ada-001"}]},prices:{input_mtok:.4,output_mtok:.4}},{id:"babbage",match:{equals:"babbage"},prices:{input_mtok:.5,output_mtok:.5}},{id:"chatgpt-4o-latest",name:"ChatGPT-4o",description:"OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of GPT-4o in that it has additional RLHF. It is intended for research and evaluation.",match:{equals:"chatgpt-4o-latest"},prices:{input_mtok:5,output_mtok:15}},{id:"codex-mini",name:"Codex Mini",description:"codex-mini-latest is a fine-tuned version of o4-mini specifically for use in Codex CLI. For direct use in the API, we recommend starting with gpt-4.1.",match:{or:[{equals:"codex-mini"},{equals:"codex-mini-latest"}]},prices:{input_mtok:1.5,cache_read_mtok:.375,output_mtok:6}},{id:"computer-use",name:"Computer use",match:{starts_with:"computer-use"},prices:{input_mtok:3,output_mtok:12}},{id:"curie",match:{or:[{equals:"curie"},{equals:"text-curie-001"}]},prices:{input_mtok:2,output_mtok:2}},{id:"davinci",match:{or:[{equals:"davinci"},{equals:"text-davinci-001"}]},prices:{input_mtok:20,output_mtok:20}},{id:"ft:gpt-3.5-turbo-",description:"GPT-3.5 Turbo fine tuned.",match:{starts_with:"ft:gpt-3.5-turbo"},prices:{input_mtok:3,output_mtok:6}},{id:"ft:gpt-4o",description:"GPT-4o fine tuned.",match:{starts_with:"ft:gpt-4o-2024-"},prices:{input_mtok:3.75,output_mtok:15}},{id:"ft:gpt-4o-mini",description:"GPT-4o Mini fine tuned.",match:{starts_with:"ft:gpt-4o-mini-2024-"},prices:{input_mtok:.3,output_mtok:1.2}},{id:"gpt-3.5-0301",match:{or:[{equals:"gpt-3.5-turbo-0301"},{equals:"gpt-3.5-0301"}]},prices:{input_mtok:1.5,output_mtok:2}},{id:"gpt-3.5-turbo",name:"gpt 3.5 turbo",description:"GPT-3.5 Turbo offers a balance between cost and performance.",match:{or:[{equals:"gpt-3.5-turbo"},{equals:"gpt-35-turbo"},{equals:"gpt-3.5-turbo-0125"}]},context_window:16385,prices:{input_mtok:.5,output_mtok:1.5}},{id:"gpt-3.5-turbo-0613",match:{equals:"gpt-3.5-turbo-0613"},context_window:16385,prices:{input_mtok:1.5,output_mtok:2}},{id:"gpt-3.5-turbo-1106",match:{equals:"gpt-3.5-turbo-1106"},context_window:16385,prices:{input_mtok:1,output_mtok:2}},{id:"gpt-3.5-turbo-16k",name:"GPT-3.5 Turbo 16k",description:"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.",match:{or:[{equals:"gpt-3.5-turbo-16k"},{equals:"gpt-3.5-turbo-16k-0613"},{equals:"gpt-35-turbo-16k-0613"},{equals:"gpt-35-turbo-16k"}]},context_window:16385,prices:{input_mtok:3,output_mtok:4}},{id:"gpt-3.5-turbo-instruct",name:"gpt 3.5 turbo instruct",description:"GPT-3.5 Turbo offers a balance between cost and performance.",match:{or:[{starts_with:"gpt-3.5-turbo-instruct"},{equals:"gpt-3.5-turbo-instruct-0914"}]},context_window:16385,prices:{input_mtok:1.5,output_mtok:2}},{id:"gpt-4",name:"gpt 4",description:"GPT-4 is the latest and most advanced model in the GPT series, demonstrating sophisticated capabilities in complex reasoning, theory of mind, and narrative understanding.",match:{or:[{equals:"gpt-4"},{equals:"gpt-4-0314"},{equals:"gpt-4-0613"},{starts_with:"ft:gpt-4-0"}]},context_window:8192,prices:{input_mtok:30,output_mtok:60}},{id:"gpt-4-32k",name:"gpt 4",description:"GPT-4 is the latest and most advanced model in the GPT series, demonstrating sophisticated capabilities in complex reasoning, theory of mind, and narrative understanding.",match:{or:[{equals:"gpt-4-32k"},{equals:"gpt-4-32k-0314"},{equals:"gpt-4-32k-0613"}]},context_window:32e3,price_comments:"see https://help.openai.com/en/articles/7127956-how-much-does-gpt-4-cost",prices:{input_mtok:60,output_mtok:120}},{id:"gpt-4-turbo",name:"gpt 4 turbo",description:"GPT-4 Turbo offers a balance between cost and performance.",match:{or:[{equals:"gpt-4-turbo"},{equals:"gpt-4-turbo-2024-04-09"},{equals:"gpt-4-turbo-0125-preview"},{equals:"gpt-4-0125-preview"},{equals:"gpt-4-1106-preview"},{equals:"gpt-4-turbo-preview"}]},context_window:128e3,prices:{input_mtok:10,output_mtok:30}},{id:"gpt-4-vision-preview",name:"gpt 4 vision",description:"GPT-4 Vision is a model that offers a balance between cost and performance.",match:{or:[{equals:"gpt-4-vision-preview"},{equals:"gpt-4-1106-vision-preview"}]},context_window:128e3,prices:{input_mtok:10,output_mtok:30}},{id:"gpt-4.1",name:"gpt 4.1",description:"GPT-4.1 is OpenAI's latest flagship model, offering major improvements in coding, instruction following, and long context understanding with up to 1 million tokens of context.",match:{or:[{equals:"gpt-4.1"},{equals:"gpt-4.1-2025-04-14"}]},context_window:1e6,prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}},{id:"gpt-4.1-mini",name:"gpt 4.1 mini",description:"GPT-4.1 Mini is a significant leap in small model performance, matching or exceeding GPT-4o in many benchmarks while reducing latency by nearly half and cost by 83%.",match:{or:[{equals:"gpt-4.1-mini"},{equals:"gpt-4.1-mini-2025-04-14"}]},context_window:1e6,prices:{input_mtok:.4,cache_read_mtok:.1,output_mtok:1.6}},{id:"gpt-4.1-nano",name:"gpt 4.1 nano",description:"GPT-4.1 Nano is OpenAI's fastest and cheapest model, delivering exceptional performance for its size with a 1 million token context window, ideal for classification and autocompletion tasks.",match:{or:[{equals:"gpt-4.1-nano"},{equals:"gpt-4.1-nano-2025-04-14"}]},context_window:1e6,prices:{input_mtok:.1,cache_read_mtok:.025,output_mtok:.4}},{id:"gpt-4.5-preview",name:"GPT-4.5 (Preview)",description:"GPT-4.5 (Preview) is a research preview of OpenAI's latest language model, designed to advance capabilities in reasoning, creativity, and multi-turn conversation. It builds on previous iterations with improvements in world knowledge, contextual coherence, and the ability to follow user intent more effectively.",match:{starts_with:"gpt-4.5-preview"},prices:{input_mtok:75,cache_read_mtok:37.5,output_mtok:150}},{id:"gpt-4o",name:"gpt 4o",description:"GPT-4 Optimized (GPT-4o) is designed for high performance in reasoning, creativity, and technical tasks while maintaining consistent output quality.",match:{or:[{equals:"gpt-4o"},{equals:"gpt-4o-2024-05-13"},{equals:"gpt-4o-2024-08-06"},{equals:"gpt-4o-2024-11-20"}]},context_window:128e3,prices:{input_mtok:2.5,cache_read_mtok:1.25,output_mtok:10}},{id:"gpt-4o-audio-preview",name:"gpt 4o audio preview",description:"Audio model for gpt-4o",match:{starts_with:"gpt-4o-audio-preview"},context_window:128e3,prices:{input_mtok:2.5,output_mtok:10,input_audio_mtok:2.5}},{id:"gpt-4o-mini",name:"gpt 4o mini",description:"GPT-4o Mini is a cost-optimized variant of GPT-4o, designed for high-efficiency processing while maintaining strong performance. It excels in rapid inference and resource-efficient operations, making it ideal for production deployments requiring a balance of cost and capability.",match:{or:[{equals:"gpt-4o-mini"},{equals:"gpt-4o-mini-2024-07-18"},{equals:"gpt-4o-mini-search-preview"},{equals:"gpt-4o-mini-search-preview-2025-03-11"}]},context_window:128e3,prices:{input_mtok:.15,cache_read_mtok:.075,output_mtok:.6}},{id:"gpt-4o-mini-2024-07-18.ft-",description:"GPT-4o Mini fine tuned.",match:{starts_with:"gpt-4o-mini-2024-07-18.ft-"},prices:{input_mtok:.3,output_mtok:1.2}},{id:"gpt-4o-mini-audio-preview",name:"gpt 4o mini audio preview",description:"Audio model for gpt-4o mini",match:{starts_with:"gpt-4o-mini-audio"},prices:{input_mtok:.15,output_mtok:.6,input_audio_mtok:.15}},{id:"gpt-4o-mini-realtime-preview",match:{starts_with:"gpt-4o-mini-realtime"},prices:{input_mtok:.6,cache_read_mtok:.3,output_mtok:2.4,input_audio_mtok:10,cache_audio_read_mtok:.3,output_audio_mtok:20}},{id:"gpt-4o-mini-transcribe",match:{equals:"gpt-4o-mini-transcribe"},prices:{input_mtok:1.25,output_mtok:5,input_audio_mtok:3}},{id:"gpt-4o-mini-tts",match:{equals:"gpt-4o-mini-tts"},prices:{input_mtok:.6,output_mtok:12,output_audio_mtok:12}},{id:"gpt-4o-realtime-preview",match:{starts_with:"gpt-4o-realtime"},prices:{input_mtok:5,cache_read_mtok:2.5,output_mtok:20,input_audio_mtok:40,cache_audio_read_mtok:2.5,output_audio_mtok:80}},{id:"gpt-4o-search-preview",name:"GPT-4o Search Preview",description:"GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.",match:{or:[{equals:"gpt-4o-search-preview"},{equals:"gpt-4o-search-preview-2025-03-11"}]},prices:{input_mtok:2.5,output_mtok:10}},{id:"gpt-4o-transcribe",match:{or:[{equals:"gpt-4o-transcribe"},{equals:"gpt-4o-transcribe-diarize"}]},prices:{input_mtok:2.5,output_mtok:10,input_audio_mtok:6}},{id:"gpt-4o:extended",name:"GPT-4o (extended)",description:`GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.`,match:{equals:"gpt-4o:extended"},prices:{input_mtok:6,output_mtok:18}},{id:"gpt-5",name:"GPT-5",description:"GPT-5 is OpenAI's flagship model for coding, reasoning, and agentic tasks across domains.",match:{or:[{equals:"gpt-5"},{equals:"gpt-5-2025-08-07"},{equals:"gpt-5-chat"},{equals:"gpt-5-chat-latest"},{equals:"gpt-5-codex"}]},context_window:4e5,prices:{input_mtok:1.25,cache_read_mtok:.125,output_mtok:10}},{id:"gpt-5-image",match:{equals:"gpt-5-image"},price_comments:"Seen on OpenRouter before OpenAI",prices:{input_mtok:10,cache_read_mtok:1.25,output_mtok:10}},{id:"gpt-5-image-mini",match:{equals:"gpt-5-image-mini"},price_comments:"Seen on OpenRouter before OpenAI",prices:{input_mtok:2.5,cache_read_mtok:.25,output_mtok:2}},{id:"gpt-5-mini",name:"GPT-5 mini",description:"GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.",match:{or:[{equals:"gpt-5-mini"},{equals:"gpt-5-mini-2025-08-07"}]},context_window:4e5,prices:{input_mtok:.25,cache_read_mtok:.025,output_mtok:2}},{id:"gpt-5-nano",name:"GPT-5 nano",description:"GPT-5 Nano is OpenAI's fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.",match:{or:[{equals:"gpt-5-nano"},{starts_with:"gpt-5-nano-"}]},context_window:4e5,prices:{input_mtok:.05,cache_read_mtok:.005,output_mtok:.4}},{id:"gpt-5-pro",match:{or:[{equals:"gpt-5-pro"},{equals:"gpt-5-pro-2025-10-06"}]},context_window:4e5,prices:{input_mtok:15,output_mtok:120}},{id:"gpt-5.1",name:"GPT-5.1",description:"The best model for coding and agentic tasks across industries",match:{or:[{equals:"gpt-5.1"},{equals:"gpt-5.1-2025-11-13"},{equals:"gpt-5.1-codex"},{equals:"gpt-5.1-codex-max"},{equals:"gpt-5.1-chat"},{equals:"gpt-5.1-chat-latest"},{equals:"gpt-5-1"},{equals:"gpt-5-1-2025-11-13"},{equals:"gpt-5-1-codex"},{equals:"gpt-5-1-codex-max"},{equals:"gpt-5-1-chat"},{equals:"gpt-5-1-chat-latest"}]},context_window:4e5,prices:{input_mtok:1.25,cache_read_mtok:.125,output_mtok:10}},{id:"gpt-5.1-codex-mini",name:"GPT-5.1 Codex Mini",match:{or:[{equals:"gpt-5.1-codex-mini"},{equals:"gpt-5.1-mini"},{equals:"gpt-5-1-codex-mini"},{equals:"gpt-5-1-mini"}]},context_window:4e5,prices:{input_mtok:.25,cache_read_mtok:.025,output_mtok:2}},{id:"gpt-5.2",name:"GPT-5.2",description:"The best model for coding and agentic tasks across industries",match:{or:[{equals:"gpt-5.2"},{equals:"gpt-5.2-2025-12-11"},{equals:"gpt-5-2"},{equals:"gpt-5-2-2025-12-11"},{equals:"gpt-5.2-chat"},{equals:"gpt-5.2-chat-latest"},{equals:"gpt-5-2-chat"},{equals:"gpt-5-2-chat-latest"},{equals:"gpt-5.2-codex"},{equals:"gpt-5-2-codex"}]},context_window:4e5,prices:{input_mtok:1.75,cache_read_mtok:.175,output_mtok:14}},{id:"gpt-5.2-pro",description:"Version of GPT-5.2 that produces smarter and more precise responses.",match:{or:[{equals:"gpt-5.2-pro"},{equals:"gpt-5.2-pro-2025-12-11"},{equals:"gpt-5-2-pro-2025-12-11"}]},context_window:4e5,prices:{input_mtok:21,output_mtok:168}},{id:"gpt-5.3",name:"GPT-5.3 Chat",description:"GPT-5.3 Instant model used in ChatGPT",match:{or:[{equals:"gpt-5.3"},{equals:"gpt-5-3"},{equals:"gpt-5.3-chat"},{equals:"gpt-5.3-chat-latest"},{equals:"gpt-5-3-chat"},{equals:"gpt-5-3-chat-latest"}]},context_window:128e3,prices:{input_mtok:1.75,cache_read_mtok:.175,output_mtok:14}},{id:"gpt-5.3-codex",name:"GPT-5.3-Codex",description:"The most capable agentic coding model",match:{or:[{equals:"gpt-5.3-codex"},{equals:"gpt-5-3-codex"}]},context_window:4e5,prices:{input_mtok:1.75,cache_read_mtok:.175,output_mtok:14}},{id:"gpt-5.4",name:"GPT-5.4",description:"OpenAI's most capable model with a 1.05M token context window.",match:{or:[{equals:"gpt-5.4"},{equals:"gpt-5.4-2026-03-05"},{equals:"gpt-5-4"},{equals:"gpt-5-4-2026-03-05"}]},context_window:105e4,prices:{input_mtok:{base:2.5,tiers:[{start:272e3,price:5}]},cache_read_mtok:{base:.25,tiers:[{start:272e3,price:.5}]},output_mtok:{base:15,tiers:[{start:272e3,price:22.5}]}}},{id:"gpt-5.4-mini",name:"GPT-5.4 mini",description:"Our strongest mini model yet for coding, computer use, and subagents.",match:{or:[{equals:"gpt-5.4-mini"},{equals:"gpt-5.4-mini-2026-03-17"},{equals:"gpt-5-4-mini"},{equals:"gpt-5-4-mini-2026-03-17"}]},context_window:4e5,prices:{input_mtok:.75,cache_read_mtok:.075,output_mtok:4.5}},{id:"gpt-5.4-nano",name:"GPT-5.4 nano",description:"Our cheapest GPT-5.4-class model for simple high-volume tasks.",match:{or:[{equals:"gpt-5.4-nano"},{equals:"gpt-5.4-nano-2026-03-17"},{equals:"gpt-5-4-nano"},{equals:"gpt-5-4-nano-2026-03-17"}]},context_window:4e5,prices:{input_mtok:.2,cache_read_mtok:.02,output_mtok:1.25}},{id:"gpt-5.4-pro",name:"GPT-5.4 Pro",description:"Version of GPT-5.4 that produces smarter and more precise responses.",match:{or:[{equals:"gpt-5.4-pro"},{equals:"gpt-5.4-pro-2026-03-05"},{equals:"gpt-5-4-pro"},{equals:"gpt-5-4-pro-2026-03-05"}]},context_window:105e4,prices:{input_mtok:{base:30,tiers:[{start:272e3,price:60}]},output_mtok:{base:180,tiers:[{start:272e3,price:270}]}}},{id:"gpt-5.5",name:"GPT-5.5",description:"The best model for coding and agentic tasks across industries",match:{or:[{equals:"gpt-5.5"},{equals:"gpt-5.5-2026-04-23"},{equals:"gpt-5.5-2026-04-24"},{equals:"gpt-5-5"},{equals:"gpt-5-5-2026-04-23"},{equals:"gpt-5-5-2026-04-24"},{equals:"gpt-5.5-chat"},{equals:"gpt-5.5-chat-latest"},{equals:"gpt-5-5-chat"},{equals:"gpt-5-5-chat-latest"},{equals:"gpt-5.5-codex"},{equals:"gpt-5-5-codex"}]},context_window:1e6,prices:{input_mtok:5,cache_read_mtok:.5,output_mtok:30}},{id:"gpt-5.5-pro",name:"GPT-5.5 Pro",description:"Version of GPT-5.5 that produces smarter and more precise responses.",match:{or:[{equals:"gpt-5.5-pro"},{equals:"gpt-5.5-pro-2026-04-23"},{equals:"gpt-5-5-pro"},{equals:"gpt-5-5-pro-2026-04-23"}]},context_window:1e6,prices:{input_mtok:30,output_mtok:180}},{id:"gpt-realtime",match:{or:[{equals:"gpt-realtime"},{equals:"gpt-realtime-2025-08-28"}]},price_comments:"Missing image token prices which we don't support yet",prices:{input_mtok:4,cache_read_mtok:.4,output_mtok:16,input_audio_mtok:32,cache_audio_read_mtok:.4,output_audio_mtok:64}},{id:"gpt-realtime-mini",match:{equals:"gpt-realtime-mini"},price_comments:"Missing image token prices which we don't support yet",prices:{input_mtok:.6,cache_read_mtok:.06,output_mtok:2.4,input_audio_mtok:10,cache_audio_read_mtok:.3,output_audio_mtok:20}},{id:"moderation",description:"All OpenAI moderation models and endpoints are free of charge",match:{contains:"moderation"},prices:{}},{id:"o1",name:"o1",description:"O1 is a model that offers a balance between cost and performance.",match:{or:[{equals:"o1"},{equals:"o1-2024-12-17"},{equals:"o1-preview"},{equals:"o1-preview-2024-09-12"}]},context_window:128e3,prices:{input_mtok:15,cache_read_mtok:7.5,output_mtok:60}},{id:"o1-mini",name:"o1 mini",description:"O1 Mini is a model that offers a balance between cost and performance.",match:{or:[{equals:"o1-mini"},{equals:"o1-mini-2024-09-12"}]},context_window:128e3,prices:{input_mtok:1.1,cache_read_mtok:.55,output_mtok:4.4}},{id:"o1-pro",name:"o1-pro",description:"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.",match:{or:[{equals:"o1-pro"},{equals:"o1-pro-2025-03-19"}]},prices:{input_mtok:150,output_mtok:600}},{id:"o3",name:"o3",description:"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images. Note that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations",match:{or:[{equals:"o3"},{equals:"o3-2025-04-16"}]},prices:[{prices:{input_mtok:10,cache_read_mtok:.5,output_mtok:40}},{constraint:{start_date:"2025-06-10",type:"start_date"},prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}}]},{id:"o3-deep-research",match:{or:[{equals:"o3-deep-research"},{equals:"o3-deep-research-2025-06-26"}]},prices:{input_mtok:10,cache_read_mtok:2.5,output_mtok:40}},{id:"o3-mini",name:"o3 Mini",description:"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding.",match:{or:[{equals:"o3-mini"},{equals:"o3-mini-2025-01-31"},{equals:"o3-mini-high"}]},prices:{input_mtok:1.1,cache_read_mtok:.55,output_mtok:4.4}},{id:"o3-pro",name:"o3 Pro",description:"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.",match:{or:[{equals:"o3-pro"},{equals:"o3-pro-2025-06-10"}]},prices:{input_mtok:20,output_mtok:80}},{id:"o4-mini",name:"o4 Mini High",description:"OpenAI o4-mini-high is the same model as o4-mini with reasoning_effort set to high.",match:{or:[{equals:"o4-mini-2025-04-16"},{equals:"o4-mini-high"},{equals:"o4-mini"}]},prices:{input_mtok:1.1,cache_read_mtok:.275,output_mtok:4.4}},{id:"o4-mini-deep-research",match:{or:[{equals:"o4-mini-deep-research"},{equals:"o4-mini-deep-research-2025-06-26"}]},prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}},{id:"text-davinci-002",match:{equals:"text-davinci-002"},prices:{input_mtok:20,output_mtok:20}},{id:"text-davinci-003",match:{equals:"text-davinci-003"},prices:{input_mtok:20,output_mtok:20}},{id:"text-embedding-3-large",name:"text embedding 3",description:"Text Embedding 3 is a model that offers a balance between cost and performance.",match:{equals:"text-embedding-3-large"},context_window:8192,prices:{input_mtok:.13}},{id:"text-embedding-3-small",name:"text embedding 3",description:"Text Embedding 3 is a model that offers a balance between cost and performance.",match:{equals:"text-embedding-3-small"},context_window:8192,prices:{input_mtok:.02}},{id:"text-embedding-ada-002",name:"text embedding ada",description:"Text Embedding Ada is a model that offers a balance between cost and performance.",match:{or:[{equals:"text-embedding-ada"},{equals:"text-embedding-ada-002"},{equals:"text-embedding-ada-002-v2"}]},context_window:8192,prices:{input_mtok:.1}}]},{id:"openrouter",name:"OpenRouter",pricing_urls:["https://openrouter.ai/models"],api_pattern:"https://(api\\.)?openrouter\\.ai",extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","cache_write_tokens"],dest:"cache_write_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"01-ai/yi-large",match:{equals:"01-ai/yi-large"},prices:{input_mtok:3,output_mtok:3}},{id:"aetherwiing/mn-starcannon-12b",match:{equals:"aetherwiing/mn-starcannon-12b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"agentica-org/deepcoder-14b-preview:free",match:{equals:"agentica-org/deepcoder-14b-preview:free"},prices:{}},{id:"ai21/jamba-1-5-large",match:{equals:"ai21/jamba-1-5-large"},prices:{input_mtok:2,output_mtok:8}},{id:"ai21/jamba-1-5-mini",match:{equals:"ai21/jamba-1-5-mini"},prices:{input_mtok:.2,output_mtok:.4}},{id:"ai21/jamba-1.6-large",match:{equals:"ai21/jamba-1.6-large"},prices:{input_mtok:2,output_mtok:8}},{id:"ai21/jamba-1.6-mini",match:{equals:"ai21/jamba-1.6-mini"},prices:{input_mtok:.2,output_mtok:.4}},{id:"ai21/jamba-instruct",match:{equals:"ai21/jamba-instruct"},prices:{input_mtok:.5,output_mtok:.7}},{id:"aion-1.0",name:"Aion-1.0",match:{equals:"aion-1.0"},prices:{input_mtok:4,output_mtok:8}},{id:"aion-1.0-mini",name:"Aion-1.0-Mini",match:{equals:"aion-1.0-mini"},prices:{input_mtok:.7,output_mtok:1.4}},{id:"aion-labs/aion-1.0",match:{equals:"aion-labs/aion-1.0"},prices:{input_mtok:4,output_mtok:8}},{id:"aion-labs/aion-1.0-mini",match:{equals:"aion-labs/aion-1.0-mini"},prices:{input_mtok:.7,output_mtok:1.4}},{id:"aion-labs/aion-rp-llama-3.1-8b",match:{equals:"aion-labs/aion-rp-llama-3.1-8b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"aion-rp-llama-3.1-8b",name:"Aion-RP 1.0 (8B)",match:{equals:"aion-rp-llama-3.1-8b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"alfredpros/codellama-7b-instruct-solidity",match:{equals:"alfredpros/codellama-7b-instruct-solidity"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"all-hands/openhands-lm-32b-v0.1",match:{equals:"all-hands/openhands-lm-32b-v0.1"},prices:{input_mtok:2.6,output_mtok:3.4}},{id:"allenai/molmo-7b-d:free",match:{equals:"allenai/molmo-7b-d:free"},prices:{}},{id:"alpindale/goliath-120b",match:{equals:"alpindale/goliath-120b"},prices:{input_mtok:6.5625,output_mtok:9.375}},{id:"alpindale/magnum-72b",match:{equals:"alpindale/magnum-72b"},prices:{input_mtok:1.5,output_mtok:2.25}},{id:"amazon/nova-lite-v1",match:{equals:"amazon/nova-lite-v1"},prices:{input_mtok:.06,output_mtok:.24}},{id:"amazon/nova-micro-v1",match:{equals:"amazon/nova-micro-v1"},prices:{input_mtok:.035,output_mtok:.14}},{id:"amazon/nova-pro-v1",match:{equals:"amazon/nova-pro-v1"},prices:{input_mtok:.8,output_mtok:3.2}},{id:"anthracite-org/magnum-v2-72b",match:{equals:"anthracite-org/magnum-v2-72b"},prices:{input_mtok:3,output_mtok:3}},{id:"anthracite-org/magnum-v4-72b",match:{equals:"anthracite-org/magnum-v4-72b"},prices:{input_mtok:1.5,output_mtok:2.25}},{id:"anthropic/claude-2",match:{or:[{equals:"anthropic/claude-2"},{equals:"anthropic/claude-2.0"},{equals:"anthropic/claude-2.0:beta"},{equals:"anthropic/claude-2.1"},{equals:"anthropic/claude-2.1:beta"},{equals:"anthropic/claude-2:beta"}]},prices:{input_mtok:8,output_mtok:24}},{id:"anthropic/claude-3-haiku",match:{or:[{equals:"anthropic/claude-3-haiku"},{equals:"anthropic/claude-3-haiku:beta"}]},prices:{input_mtok:.25,output_mtok:1.25}},{id:"anthropic/claude-3-opus",match:{or:[{equals:"anthropic/claude-3-opus"},{equals:"anthropic/claude-3-opus:beta"}]},prices:{input_mtok:15,output_mtok:75}},{id:"anthropic/claude-3-sonnet",match:{or:[{equals:"anthropic/claude-3-sonnet"},{equals:"anthropic/claude-3-sonnet:beta"}]},prices:{input_mtok:3,output_mtok:15}},{id:"anthropic/claude-3.5-haiku",match:{or:[{equals:"anthropic/claude-3.5-haiku"},{equals:"anthropic/claude-3.5-haiku-20241022"},{equals:"anthropic/claude-3.5-haiku-20241022:beta"},{equals:"anthropic/claude-3.5-haiku:beta"}]},prices:{input_mtok:.8,output_mtok:4}},{id:"anthropic/claude-3.5-sonnet",match:{or:[{equals:"anthropic/claude-3.5-sonnet"},{equals:"anthropic/claude-3.5-sonnet-20240620"},{equals:"anthropic/claude-3.5-sonnet-20240620:beta"},{equals:"anthropic/claude-3.5-sonnet:beta"}]},prices:{input_mtok:3,output_mtok:15}},{id:"anthropic/claude-3.7-sonnet",match:{or:[{equals:"anthropic/claude-3.7-sonnet"},{equals:"anthropic/claude-3.7-sonnet:beta"},{equals:"anthropic/claude-3.7-sonnet:thinking"}]},prices:{input_mtok:3,output_mtok:15}},{id:"anthropic/claude-fable-5",match:{or:[{equals:"anthropic/claude-fable-5"},{equals:"anthropic/claude-fable-5:beta"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:10,cache_write_mtok:12.5,cache_read_mtok:1,output_mtok:50}},{id:"anthropic/claude-haiku-4.5",match:{or:[{equals:"anthropic/claude-haiku-4.5"},{equals:"anthropic/claude-4.5-haiku-20251001"},{equals:"anthropic/claude-4.5-haiku-20251001:beta"},{equals:"anthropic/claude-haiku-4.5-20251001"},{equals:"anthropic/claude-haiku-4.5-20251001:beta"},{equals:"anthropic/claude-haiku-4.5:beta"}]},prices:{input_mtok:1,cache_write_mtok:1.25,cache_read_mtok:.1,output_mtok:5}},{id:"anthropic/claude-opus-4.5",match:{or:[{equals:"anthropic/claude-opus-4.5"},{equals:"anthropic/claude-4.5-opus-20251124"},{equals:"anthropic/claude-4.5-opus-20251124:beta"},{equals:"anthropic/claude-opus-4.5-20251124"},{equals:"anthropic/claude-opus-4.5-20251124:beta"},{equals:"anthropic/claude-opus-4.5:beta"}]},prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"anthropic/claude-opus-4.6",match:{or:[{equals:"anthropic/claude-opus-4.6"},{equals:"anthropic/claude-4.6-opus-20260205"},{equals:"anthropic/claude-4.6-opus-20260205:beta"},{equals:"anthropic/claude-opus-4.6-20260205"},{equals:"anthropic/claude-opus-4.6-20260205:beta"},{equals:"anthropic/claude-opus-4.6:beta"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"anthropic/claude-opus-4.7",match:{or:[{equals:"anthropic/claude-opus-4.7"},{equals:"anthropic/claude-opus-4.7:beta"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"anthropic/claude-opus-4.8",match:{or:[{equals:"anthropic/claude-opus-4.8"},{equals:"anthropic/claude-opus-4.8:beta"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"anthropic/claude-sonnet-4.5",match:{or:[{equals:"anthropic/claude-sonnet-4.5"},{equals:"anthropic/claude-4.5-sonnet-20250929"},{equals:"anthropic/claude-4.5-sonnet-20250929:beta"},{equals:"anthropic/claude-sonnet-4.5-20250929"},{equals:"anthropic/claude-sonnet-4.5-20250929:beta"},{equals:"anthropic/claude-sonnet-4.5:beta"}]},context_window:1e6,price_comments:"Tiered pricing: Unlike 4.6 models, Sonnet 4.5 has long-context surcharge. Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:{base:3,tiers:[{start:2e5,price:6}]},cache_write_mtok:{base:3.75,tiers:[{start:2e5,price:7.5}]},cache_read_mtok:{base:.3,tiers:[{start:2e5,price:.6}]},output_mtok:{base:15,tiers:[{start:2e5,price:22.5}]}}},{id:"anthropic/claude-sonnet-4.6",match:{or:[{equals:"anthropic/claude-sonnet-4.6"},{equals:"anthropic/claude-4.6-sonnet-20260217"},{equals:"anthropic/claude-4.6-sonnet-20260217:beta"},{equals:"anthropic/claude-sonnet-4.6-20260217"},{equals:"anthropic/claude-sonnet-4.6-20260217:beta"},{equals:"anthropic/claude-sonnet-4.6:beta"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"anubis-pro-105b-v1",name:"Anubis Pro 105B V1",match:{equals:"anubis-pro-105b-v1"},prices:{input_mtok:.8,output_mtok:1}},{id:"arcee-blitz",name:"Arcee Blitz",match:{equals:"arcee-blitz"},prices:{input_mtok:.45,output_mtok:.75}},{id:"arliai/qwq-32b-arliai-rpr-v1:free",match:{equals:"arliai/qwq-32b-arliai-rpr-v1:free"},prices:{}},{id:"bytedance-research/ui-tars-72b:free",match:{equals:"bytedance-research/ui-tars-72b:free"},prices:{}},{id:"caller-large",name:"Caller Large",match:{equals:"caller-large"},prices:{input_mtok:.55,output_mtok:.85}},{id:"chatgpt-4o-latest",name:"ChatGPT-4o",match:{equals:"chatgpt-4o-latest"},prices:{input_mtok:5,output_mtok:15}},{id:"claude-2",name:"Claude v2",match:{or:[{equals:"claude-2"},{equals:"claude-2.0"},{equals:"claude-2.0:beta"},{equals:"claude-2.1"},{equals:"claude-2.1:beta"},{equals:"claude-2:beta"}]},prices:{input_mtok:8,output_mtok:24}},{id:"claude-3-haiku",name:"Claude 3 Haiku",match:{or:[{equals:"claude-3-haiku"},{equals:"claude-3-haiku:beta"}]},prices:{input_mtok:.25,cache_write_mtok:.3,cache_read_mtok:.03,output_mtok:1.25}},{id:"claude-3-opus",name:"Claude 3 Opus",match:{or:[{equals:"claude-3-opus"},{equals:"claude-3-opus:beta"}]},prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"claude-3-sonnet",name:"Claude 3 Sonnet",match:{or:[{equals:"claude-3-sonnet"},{equals:"claude-3-sonnet:beta"}]},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-3.5-haiku",name:"Claude 3.5 Haiku",match:{or:[{equals:"claude-3.5-haiku"},{equals:"claude-3.5-haiku-20241022"},{equals:"claude-3.5-haiku-20241022:beta"},{equals:"claude-3.5-haiku:beta"}]},prices:{input_mtok:.8,cache_write_mtok:1,cache_read_mtok:.08,output_mtok:4}},{id:"claude-3.5-sonnet",name:"Claude 3.5 Sonnet",match:{or:[{equals:"claude-3.5-sonnet"},{equals:"claude-3.5-sonnet-20240620"},{equals:"claude-3.5-sonnet-20240620:beta"},{equals:"claude-3.5-sonnet:beta"}]},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-3.7-sonnet",name:"Claude 3.7 Sonnet",match:{or:[{equals:"claude-3.7-sonnet"},{equals:"claude-3.7-sonnet:beta"},{equals:"claude-3.7-sonnet:thinking"}]},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-opus-4",name:"Claude Opus 4",match:{equals:"claude-opus-4"},prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"claude-sonnet-4",name:"Claude Sonnet 4",match:{equals:"claude-sonnet-4"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"codellama-7b-instruct-solidity",name:"CodeLLaMa 7B Instruct Solidity",match:{equals:"codellama-7b-instruct-solidity"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"coder-large",name:"Coder Large",match:{equals:"coder-large"},prices:{input_mtok:.5,output_mtok:.8}},{id:"codestral-2501",name:"Codestral 2501",match:{equals:"codestral-2501"},prices:{input_mtok:.3,output_mtok:.9}},{id:"codex-mini",name:"Codex Mini",match:{equals:"codex-mini"},prices:{input_mtok:1.5,cache_read_mtok:.375,output_mtok:6}},{id:"cognitivecomputations/dolphin-mixtral-8x22b",match:{equals:"cognitivecomputations/dolphin-mixtral-8x22b"},prices:{input_mtok:.9,output_mtok:.9}},{id:"cognitivecomputations/dolphin-mixtral-8x7b",match:{equals:"cognitivecomputations/dolphin-mixtral-8x7b"},prices:{input_mtok:.5,output_mtok:.5}},{id:"cognitivecomputations/dolphin3.0-mistral-24b:free",match:{equals:"cognitivecomputations/dolphin3.0-mistral-24b:free"},prices:{}},{id:"cognitivecomputations/dolphin3.0-r1-mistral-24b:free",match:{equals:"cognitivecomputations/dolphin3.0-r1-mistral-24b:free"},prices:{}},{id:"cohere/command",match:{equals:"cohere/command"},prices:{input_mtok:1,output_mtok:2}},{id:"cohere/command-a",match:{equals:"cohere/command-a"},prices:{input_mtok:2.5,output_mtok:10}},{id:"cohere/command-r",match:{or:[{equals:"cohere/command-r"},{equals:"cohere/command-r-03-2024"}]},prices:{input_mtok:.5,output_mtok:1.5}},{id:"cohere/command-r-08-2024",match:{equals:"cohere/command-r-08-2024"},prices:{input_mtok:.15,output_mtok:.6}},{id:"cohere/command-r-plus",match:{or:[{equals:"cohere/command-r-plus"},{equals:"cohere/command-r-plus-04-2024"}]},prices:{input_mtok:3,output_mtok:15}},{id:"cohere/command-r-plus-08-2024",match:{equals:"cohere/command-r-plus-08-2024"},prices:{input_mtok:2.5,output_mtok:10}},{id:"cohere/command-r7b-12-2024",match:{equals:"cohere/command-r7b-12-2024"},prices:{input_mtok:.0375,output_mtok:.15}},{id:"command",name:"Command",match:{equals:"command"},prices:{input_mtok:1,output_mtok:2}},{id:"command-a",name:"Command A",match:{equals:"command-a"},prices:{input_mtok:2.5,output_mtok:10}},{id:"command-r",name:"Command R",match:{or:[{equals:"command-r"},{equals:"command-r-03-2024"}]},prices:{input_mtok:.5,output_mtok:1.5}},{id:"command-r-08-2024",name:"Command R (08-2024)",match:{equals:"command-r-08-2024"},prices:{input_mtok:.15,output_mtok:.6}},{id:"command-r-plus",name:"Command R+",match:{or:[{equals:"command-r-plus"},{equals:"command-r-plus-04-2024"}]},prices:{input_mtok:3,output_mtok:15}},{id:"command-r-plus-08-2024",name:"Command R+ (08-2024)",match:{equals:"command-r-plus-08-2024"},prices:{input_mtok:2.5,output_mtok:10}},{id:"command-r7b-12-2024",name:"Command R7B (12-2024)",match:{equals:"command-r7b-12-2024"},prices:{input_mtok:.0375,output_mtok:.15}},{id:"deepcoder-14b-preview:free",name:"Deepcoder 14B Preview (free)",match:{equals:"deepcoder-14b-preview:free"},prices:{}},{id:"deephermes-3-llama-3-8b-preview:free",name:"DeepHermes 3 Llama 3 8B Preview (free)",match:{equals:"deephermes-3-llama-3-8b-preview:free"},prices:{}},{id:"deepseek-chat",name:"DeepSeek V3",match:{equals:"deepseek-chat"},prices:{input_mtok:.38,output_mtok:.89}},{id:"deepseek-chat-v3-0324",name:"DeepSeek V3 0324",match:{equals:"deepseek-chat-v3-0324"},prices:{input_mtok:.3,output_mtok:.88}},{id:"deepseek-chat-v3-0324:free",name:"DeepSeek V3 0324 (free)",match:{equals:"deepseek-chat-v3-0324:free"},prices:{}},{id:"deepseek-chat:free",name:"DeepSeek V3 (free)",match:{equals:"deepseek-chat:free"},prices:{}},{id:"deepseek-prover-v2",name:"DeepSeek Prover V2",match:{equals:"deepseek-prover-v2"},prices:{input_mtok:.5,output_mtok:2.18}},{id:"deepseek-r1",name:"R1",match:{equals:"deepseek-r1"},prices:{input_mtok:.45,output_mtok:2.15}},{id:"deepseek-r1-0528",name:"R1 0528",match:{equals:"deepseek-r1-0528"},prices:{input_mtok:.5,output_mtok:2.15}},{id:"deepseek-r1-0528-qwen3-8b",name:"Deepseek R1 0528 Qwen3 8B",match:{equals:"deepseek-r1-0528-qwen3-8b"},prices:{input_mtok:.05,output_mtok:.1}},{id:"deepseek-r1-0528-qwen3-8b:free",name:"Deepseek R1 0528 Qwen3 8B (free)",match:{equals:"deepseek-r1-0528-qwen3-8b:free"},prices:{}},{id:"deepseek-r1-0528:free",name:"R1 0528 (free)",match:{equals:"deepseek-r1-0528:free"},prices:{}},{id:"deepseek-r1-distill-llama-70b",name:"R1 Distill Llama 70B",match:{equals:"deepseek-r1-distill-llama-70b"},prices:{input_mtok:.1,output_mtok:.4}},{id:"deepseek-r1-distill-llama-70b:free",name:"R1 Distill Llama 70B (free)",match:{equals:"deepseek-r1-distill-llama-70b:free"},prices:{}},{id:"deepseek-r1-distill-llama-8b",name:"R1 Distill Llama 8B",match:{equals:"deepseek-r1-distill-llama-8b"},prices:{input_mtok:.04,output_mtok:.04}},{id:"deepseek-r1-distill-qwen-1.5b",name:"R1 Distill Qwen 1.5B",match:{equals:"deepseek-r1-distill-qwen-1.5b"},prices:{input_mtok:.18,output_mtok:.18}},{id:"deepseek-r1-distill-qwen-14b",name:"R1 Distill Qwen 14B",match:{equals:"deepseek-r1-distill-qwen-14b"},prices:{input_mtok:.15,output_mtok:.15}},{id:"deepseek-r1-distill-qwen-14b:free",name:"R1 Distill Qwen 14B (free)",match:{equals:"deepseek-r1-distill-qwen-14b:free"},prices:{}},{id:"deepseek-r1-distill-qwen-32b",name:"R1 Distill Qwen 32B",match:{equals:"deepseek-r1-distill-qwen-32b"},prices:{input_mtok:.12,output_mtok:.18}},{id:"deepseek-r1-distill-qwen-32b:free",name:"R1 Distill Qwen 32B (free)",match:{equals:"deepseek-r1-distill-qwen-32b:free"},prices:{}},{id:"deepseek-r1-distill-qwen-7b",name:"R1 Distill Qwen 7B",match:{equals:"deepseek-r1-distill-qwen-7b"},prices:{input_mtok:.1,output_mtok:.2}},{id:"deepseek-r1:free",name:"R1 (free)",match:{equals:"deepseek-r1:free"},prices:{}},{id:"deepseek-r1t-chimera:free",name:"DeepSeek R1T Chimera (free)",match:{equals:"deepseek-r1t-chimera:free"},prices:{}},{id:"deepseek-v3-base:free",name:"DeepSeek V3 Base (free)",match:{equals:"deepseek-v3-base:free"},prices:{}},{id:"deepseek-v3.1-terminus",name:"DeepSeek V3.1 Terminus",match:{equals:"deepseek-v3.1-terminus"},context_window:163840,prices:{input_mtok:.23,output_mtok:.9}},{id:"deepseek/deepseek-chat",match:{equals:"deepseek/deepseek-chat"},prices:{input_mtok:.38,output_mtok:.89}},{id:"deepseek/deepseek-chat-v3-0324",match:{equals:"deepseek/deepseek-chat-v3-0324"},prices:{input_mtok:.27,output_mtok:1.1}},{id:"deepseek/deepseek-chat-v3-0324:free",match:{equals:"deepseek/deepseek-chat-v3-0324:free"},prices:{}},{id:"deepseek/deepseek-chat-v3.1",name:"DeepSeek Chat V3.1",match:{equals:"deepseek/deepseek-chat-v3.1"},context_window:163840,prices:{input_mtok:.2,output_mtok:.8}},{id:"deepseek/deepseek-chat:free",match:{equals:"deepseek/deepseek-chat:free"},prices:{}},{id:"deepseek/deepseek-r1",match:{equals:"deepseek/deepseek-r1"},prices:{input_mtok:.5,output_mtok:3}},{id:"deepseek/deepseek-r1-distill-llama-70b",match:{equals:"deepseek/deepseek-r1-distill-llama-70b"},prices:{input_mtok:.1,output_mtok:.4}},{id:"deepseek/deepseek-r1-distill-llama-70b:free",match:{equals:"deepseek/deepseek-r1-distill-llama-70b:free"},prices:{}},{id:"deepseek/deepseek-r1-distill-llama-8b",match:{equals:"deepseek/deepseek-r1-distill-llama-8b"},prices:{input_mtok:.04,output_mtok:.04}},{id:"deepseek/deepseek-r1-distill-qwen-1.5b",match:{equals:"deepseek/deepseek-r1-distill-qwen-1.5b"},prices:{input_mtok:.18,output_mtok:.18}},{id:"deepseek/deepseek-r1-distill-qwen-14b",match:{equals:"deepseek/deepseek-r1-distill-qwen-14b"},prices:{input_mtok:.15,output_mtok:.15}},{id:"deepseek/deepseek-r1-distill-qwen-14b:free",match:{equals:"deepseek/deepseek-r1-distill-qwen-14b:free"},prices:{}},{id:"deepseek/deepseek-r1-distill-qwen-32b",match:{equals:"deepseek/deepseek-r1-distill-qwen-32b"},prices:{input_mtok:.12,output_mtok:.18}},{id:"deepseek/deepseek-r1-distill-qwen-32b:free",match:{equals:"deepseek/deepseek-r1-distill-qwen-32b:free"},prices:{}},{id:"deepseek/deepseek-r1-zero:free",match:{equals:"deepseek/deepseek-r1-zero:free"},prices:{}},{id:"deepseek/deepseek-r1:free",match:{equals:"deepseek/deepseek-r1:free"},prices:{}},{id:"deepseek/deepseek-v3-base:free",match:{equals:"deepseek/deepseek-v3-base:free"},prices:{}},{id:"deepseek/deepseek-v3.2",name:"DeepSeek V3.2",match:{equals:"deepseek/deepseek-v3.2"},context_window:131072,prices:{input_mtok:.252,cache_read_mtok:.0252,output_mtok:.378}},{id:"deepseek/deepseek-v3.2-exp",name:"DeepSeek V3.2 Experimental",match:{equals:"deepseek/deepseek-v3.2-exp"},prices:{input_mtok:.27,output_mtok:.4}},{id:"devstral-small",name:"Devstral Small",match:{equals:"devstral-small"},prices:{input_mtok:.06,output_mtok:.12}},{id:"devstral-small:free",name:"Devstral Small (free)",match:{equals:"devstral-small:free"},prices:{}},{id:"dobby-mini-unhinged-plus-llama-3.1-8b",name:"Dobby Mini Plus Llama 3.1 8B",match:{equals:"dobby-mini-unhinged-plus-llama-3.1-8b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"dolphin-mixtral-8x22b",name:"Dolphin 2.9.2 Mixtral 8x22B 🐬",match:{equals:"dolphin-mixtral-8x22b"},prices:{input_mtok:.9,output_mtok:.9}},{id:"dolphin3.0-mistral-24b:free",name:"Dolphin3.0 Mistral 24B (free)",match:{equals:"dolphin3.0-mistral-24b:free"},prices:{}},{id:"dolphin3.0-r1-mistral-24b:free",name:"Dolphin3.0 R1 Mistral 24B (free)",match:{equals:"dolphin3.0-r1-mistral-24b:free"},prices:{}},{id:"eleutherai/llemma_7b",match:{equals:"eleutherai/llemma_7b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"eva-llama-3.33-70b",name:"EVA Llama 3.33 70B",match:{equals:"eva-llama-3.33-70b"},prices:{input_mtok:4,output_mtok:6}},{id:"eva-qwen-2.5-32b",name:"EVA Qwen2.5 32B",match:{equals:"eva-qwen-2.5-32b"},prices:{input_mtok:2.6,output_mtok:3.4}},{id:"eva-qwen-2.5-72b",name:"EVA Qwen2.5 72B",match:{equals:"eva-qwen-2.5-72b"},prices:{input_mtok:4,output_mtok:6}},{id:"eva-unit-01/eva-llama-3.33-70b",match:{equals:"eva-unit-01/eva-llama-3.33-70b"},prices:{input_mtok:4,output_mtok:6}},{id:"eva-unit-01/eva-qwen-2.5-32b",match:{equals:"eva-unit-01/eva-qwen-2.5-32b"},prices:{input_mtok:2.6,output_mtok:3.4}},{id:"eva-unit-01/eva-qwen-2.5-72b",match:{equals:"eva-unit-01/eva-qwen-2.5-72b"},prices:{input_mtok:.9,output_mtok:1.2}},{id:"featherless/qwerky-72b:free",match:{equals:"featherless/qwerky-72b:free"},prices:{}},{id:"fimbulvetr-11b-v2",name:"Fimbulvetr 11B v2",match:{equals:"fimbulvetr-11b-v2"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"gemini-2.0-flash-001",name:"Gemini 2.0 Flash",match:{equals:"gemini-2.0-flash-001"},prices:{input_mtok:.1,cache_write_mtok:.1833,cache_read_mtok:.025,output_mtok:.4}},{id:"gemini-2.0-flash-exp:free",name:"Gemini 2.0 Flash Experimental (free)",match:{equals:"gemini-2.0-flash-exp:free"},prices:{}},{id:"gemini-2.0-flash-lite-001",name:"Gemini 2.0 Flash Lite",match:{equals:"gemini-2.0-flash-lite-001"},prices:{input_mtok:.075,output_mtok:.3}},{id:"gemini-2.5-flash",name:"Gemini 2.5 Flash",match:{or:[{equals:"gemini-2.5-flash"},{equals:"google/gemini-2.5-flash"}]},prices:{input_mtok:.3,cache_write_mtok:.3833,cache_read_mtok:.075,output_mtok:2.5}},{id:"gemini-2.5-flash-lite-preview-06-17",name:"Gemini 2.5 Flash Lite Preview 06-17",match:{equals:"gemini-2.5-flash-lite-preview-06-17"},prices:{input_mtok:.1,output_mtok:.4}},{id:"gemini-2.5-flash-preview",name:"Gemini 2.5 Flash Preview 04-17",match:{or:[{equals:"gemini-2.5-flash-preview"},{equals:"gemini-2.5-flash-preview-05-20"}]},prices:{input_mtok:.15,cache_write_mtok:.2333,cache_read_mtok:.0375,output_mtok:.6}},{id:"gemini-2.5-flash-preview-05-20:thinking",name:"Gemini 2.5 Flash Preview 05-20 (thinking)",match:{equals:"gemini-2.5-flash-preview-05-20:thinking"},prices:{input_mtok:.15,cache_write_mtok:.2333,cache_read_mtok:.0375,output_mtok:3.5}},{id:"gemini-2.5-flash-preview:thinking",name:"Gemini 2.5 Flash Preview 04-17 (thinking)",match:{equals:"gemini-2.5-flash-preview:thinking"},prices:{input_mtok:.15,cache_write_mtok:.2333,cache_read_mtok:.0375,output_mtok:3.5}},{id:"gemini-2.5-pro",name:"Gemini 2.5 Pro",match:{or:[{equals:"gemini-2.5-pro"},{equals:"gemini-2.5-pro-preview"},{equals:"gemini-2.5-pro-preview-05-06"},{equals:"google/gemini-2.5-pro"},{equals:"google/gemini-2.5-pro-preview"},{equals:"google/gemini-2.5-pro-preview-05-06"}]},prices:{input_mtok:1.25,cache_write_mtok:1.625,cache_read_mtok:.31,output_mtok:10}},{id:"gemini-2.5-pro-exp-03-25",name:"Gemini 2.5 Pro Experimental",match:{equals:"gemini-2.5-pro-exp-03-25"},prices:{}},{id:"gemini-flash-1.5",name:"Gemini 1.5 Flash",match:{equals:"gemini-flash-1.5"},prices:{input_mtok:.075,cache_write_mtok:.1583,cache_read_mtok:.01875,output_mtok:.3}},{id:"gemini-flash-1.5-8b",name:"Gemini 1.5 Flash 8B",match:{equals:"gemini-flash-1.5-8b"},prices:{input_mtok:.0375,cache_write_mtok:.0583,cache_read_mtok:.01,output_mtok:.15}},{id:"gemini-pro-1.5",name:"Gemini 1.5 Pro",match:{equals:"gemini-pro-1.5"},prices:{input_mtok:1.25,output_mtok:5}},{id:"gemma-2-27b-it",name:"Gemma 2 27B",match:{equals:"gemma-2-27b-it"},prices:{input_mtok:.8,output_mtok:.8}},{id:"gemma-2-9b-it",name:"Gemma 2 9B",match:{equals:"gemma-2-9b-it"},prices:{input_mtok:.2,output_mtok:.2}},{id:"gemma-2-9b-it:free",name:"Gemma 2 9B (free)",match:{equals:"gemma-2-9b-it:free"},prices:{}},{id:"gemma-3-12b-it",name:"Gemma 3 12B",match:{equals:"gemma-3-12b-it"},prices:{input_mtok:.05,output_mtok:.1}},{id:"gemma-3-12b-it:free",name:"Gemma 3 12B (free)",match:{equals:"gemma-3-12b-it:free"},prices:{}},{id:"gemma-3-27b-it",name:"Gemma 3 27B",match:{equals:"gemma-3-27b-it"},prices:{input_mtok:.1,output_mtok:.2}},{id:"gemma-3-27b-it:free",name:"Gemma 3 27B (free)",match:{equals:"gemma-3-27b-it:free"},prices:{}},{id:"gemma-3-4b-it",name:"Gemma 3 4B",match:{equals:"gemma-3-4b-it"},prices:{input_mtok:.02,output_mtok:.04}},{id:"gemma-3-4b-it:free",name:"Gemma 3 4B (free)",match:{equals:"gemma-3-4b-it:free"},prices:{}},{id:"gemma-3n-e4b-it:free",name:"Gemma 3n 4B (free)",match:{equals:"gemma-3n-e4b-it:free"},prices:{}},{id:"glm-4-32b",name:"GLM 4 32B",match:{equals:"glm-4-32b"},prices:{input_mtok:.24,output_mtok:.24}},{id:"glm-4-32b:free",name:"GLM 4 32B (free)",match:{equals:"glm-4-32b:free"},prices:{}},{id:"glm-z1-32b",name:"GLM Z1 32B",match:{equals:"glm-z1-32b"},prices:{input_mtok:.24,output_mtok:.24}},{id:"glm-z1-32b:free",name:"GLM Z1 32B (free)",match:{equals:"glm-z1-32b:free"},prices:{}},{id:"glm-z1-rumination-32b",name:"GLM Z1 Rumination 32B",match:{equals:"glm-z1-rumination-32b"},prices:{input_mtok:.24,output_mtok:.24}},{id:"goliath-120b",name:"Goliath 120B",match:{equals:"goliath-120b"},prices:{input_mtok:10,output_mtok:12.5}},{id:"google/gemini-2.0-flash-001",match:{equals:"google/gemini-2.0-flash-001"},prices:{input_mtok:.1,output_mtok:.4}},{id:"google/gemini-2.0-flash-exp:free",match:{equals:"google/gemini-2.0-flash-exp:free"},prices:{}},{id:"google/gemini-2.0-flash-lite-001",match:{equals:"google/gemini-2.0-flash-lite-001"},prices:{input_mtok:.075,output_mtok:.3}},{id:"google/gemini-2.0-flash-thinking-exp-1219:free",match:{equals:"google/gemini-2.0-flash-thinking-exp-1219:free"},prices:{}},{id:"google/gemini-2.0-flash-thinking-exp:free",match:{equals:"google/gemini-2.0-flash-thinking-exp:free"},prices:{}},{id:"google/gemini-2.5-flash-image",name:"Gemini 2.5 Flash Image (Nano Banana)",match:{or:[{equals:"google/gemini-2.5-flash-image"},{equals:"google/gemini-2.5-flash-image-preview"}]},prices:{input_mtok:.3,output_mtok:2.5}},{id:"google/gemini-2.5-flash-lite",name:"Gemini 2.5 Flash Lite",match:{equals:"google/gemini-2.5-flash-lite"},prices:{input_mtok:.1,cache_write_mtok:.183,cache_read_mtok:.025,output_mtok:.4}},{id:"google/gemini-2.5-flash-lite-preview-09-2025",name:"Gemini 2.5 Flash Lite Preview 09-2025",match:{equals:"google/gemini-2.5-flash-lite-preview-09-2025"},prices:{input_mtok:.1,output_mtok:.4}},{id:"google/gemini-2.5-flash-preview",match:{equals:"google/gemini-2.5-flash-preview"},prices:{input_mtok:.15,output_mtok:.6}},{id:"google/gemini-2.5-flash-preview-09-2025",name:"Gemini 2.5 Flash Preview 09-2025",match:{equals:"google/gemini-2.5-flash-preview-09-2025"},prices:{input_mtok:.3,cache_write_mtok:.383,cache_read_mtok:.075,output_mtok:2.5}},{id:"google/gemini-2.5-flash-preview:thinking",match:{equals:"google/gemini-2.5-flash-preview:thinking"},prices:{input_mtok:.15,output_mtok:3.5}},{id:"google/gemini-2.5-pro-exp-03-25:free",match:{equals:"google/gemini-2.5-pro-exp-03-25:free"},prices:{}},{id:"google/gemini-2.5-pro-preview-03-25",match:{equals:"google/gemini-2.5-pro-preview-03-25"},prices:{input_mtok:1.25,output_mtok:10}},{id:"google/gemini-flash-1.5",match:{equals:"google/gemini-flash-1.5"},prices:{input_mtok:.075,output_mtok:.3}},{id:"google/gemini-flash-1.5-8b",match:{equals:"google/gemini-flash-1.5-8b"},prices:{input_mtok:.0375,output_mtok:.15}},{id:"google/gemini-flash-1.5-8b-exp",match:{equals:"google/gemini-flash-1.5-8b-exp"},prices:{}},{id:"google/gemini-pro",match:{or:[{equals:"google/gemini-pro"},{equals:"google/gemini-pro-vision"}]},prices:{input_mtok:.5,output_mtok:1.5}},{id:"google/gemini-pro-1.5",match:{equals:"google/gemini-pro-1.5"},prices:{input_mtok:1.25,output_mtok:5}},{id:"google/gemma-2-27b-it",match:{equals:"google/gemma-2-27b-it"},prices:{input_mtok:.8,output_mtok:.8}},{id:"google/gemma-2-9b-it",match:{equals:"google/gemma-2-9b-it"},prices:{input_mtok:.07,output_mtok:.07}},{id:"google/gemma-2-9b-it:free",match:{equals:"google/gemma-2-9b-it:free"},prices:{}},{id:"google/gemma-3-12b-it",match:{equals:"google/gemma-3-12b-it"},prices:{input_mtok:.05,output_mtok:.1}},{id:"google/gemma-3-12b-it:free",match:{equals:"google/gemma-3-12b-it:free"},prices:{}},{id:"google/gemma-3-1b-it:free",match:{equals:"google/gemma-3-1b-it:free"},prices:{}},{id:"google/gemma-3-27b-it",match:{equals:"google/gemma-3-27b-it"},prices:{input_mtok:.1,output_mtok:.2}},{id:"google/gemma-3-27b-it:free",match:{equals:"google/gemma-3-27b-it:free"},prices:{}},{id:"google/gemma-3-4b-it",match:{equals:"google/gemma-3-4b-it"},prices:{input_mtok:.02,output_mtok:.04}},{id:"google/gemma-3-4b-it:free",match:{equals:"google/gemma-3-4b-it:free"},prices:{}},{id:"google/learnlm-1.5-pro-experimental:free",match:{equals:"google/learnlm-1.5-pro-experimental:free"},prices:{}},{id:"google/palm-2-chat-bison",match:{or:[{equals:"google/palm-2-chat-bison"},{equals:"google/palm-2-chat-bison-32k"}]},prices:{input_mtok:1,output_mtok:2}},{id:"google/palm-2-codechat-bison",match:{or:[{equals:"google/palm-2-codechat-bison"},{equals:"google/palm-2-codechat-bison-32k"}]},prices:{input_mtok:1,output_mtok:2}},{id:"gpt-3.5-turbo",name:"GPT-3.5 Turbo",match:{or:[{equals:"gpt-3.5-turbo"},{equals:"gpt-3.5-turbo-0125"}]},prices:{input_mtok:.5,output_mtok:1.5}},{id:"gpt-3.5-turbo-0613",name:"GPT-3.5 Turbo (older v0613)",match:{equals:"gpt-3.5-turbo-0613"},prices:{input_mtok:1,output_mtok:2}},{id:"gpt-3.5-turbo-1106",name:"GPT-3.5 Turbo 16k (older v1106)",match:{equals:"gpt-3.5-turbo-1106"},prices:{input_mtok:1,output_mtok:2}},{id:"gpt-3.5-turbo-16k",name:"GPT-3.5 Turbo 16k",match:{equals:"gpt-3.5-turbo-16k"},prices:{input_mtok:3,output_mtok:4}},{id:"gpt-3.5-turbo-instruct",name:"GPT-3.5 Turbo Instruct",match:{equals:"gpt-3.5-turbo-instruct"},prices:{input_mtok:1.5,output_mtok:2}},{id:"gpt-4",name:"GPT-4",match:{or:[{equals:"gpt-4"},{equals:"gpt-4-0314"}]},prices:{input_mtok:30,output_mtok:60}},{id:"gpt-4-1106-preview",name:"GPT-4 Turbo (older v1106)",match:{equals:"gpt-4-1106-preview"},prices:{input_mtok:10,output_mtok:30}},{id:"gpt-4-turbo",name:"GPT-4 Turbo",match:{or:[{equals:"gpt-4-turbo"},{equals:"gpt-4-turbo-preview"}]},prices:{input_mtok:10,output_mtok:30}},{id:"gpt-4.1",name:"GPT-4.1",match:{equals:"gpt-4.1"},prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}},{id:"gpt-4.1-mini",name:"GPT-4.1 Mini",match:{equals:"gpt-4.1-mini"},prices:{input_mtok:.4,cache_read_mtok:.1,output_mtok:1.6}},{id:"gpt-4.1-nano",name:"GPT-4.1 Nano",match:{equals:"gpt-4.1-nano"},prices:{input_mtok:.1,cache_read_mtok:.025,output_mtok:.4}},{id:"gpt-4.5-preview",name:"GPT-4.5 (Preview)",match:{equals:"gpt-4.5-preview"},prices:{input_mtok:75,cache_read_mtok:37.5,output_mtok:150}},{id:"gpt-4o",name:"GPT-4o",match:{or:[{equals:"gpt-4o"},{equals:"gpt-4o-2024-08-06"},{equals:"gpt-4o-2024-11-20"}]},prices:{input_mtok:2.5,cache_read_mtok:1.25,output_mtok:10}},{id:"gpt-4o-2024-05-13",name:"GPT-4o (2024-05-13)",match:{equals:"gpt-4o-2024-05-13"},prices:{input_mtok:5,output_mtok:15}},{id:"gpt-4o-mini",name:"GPT-4o-mini",match:{or:[{equals:"gpt-4o-mini"},{equals:"gpt-4o-mini-2024-07-18"}]},prices:{input_mtok:.15,cache_read_mtok:.075,output_mtok:.6}},{id:"gpt-4o-mini-search-preview",name:"GPT-4o-mini Search Preview",match:{equals:"gpt-4o-mini-search-preview"},prices:{input_mtok:.15,output_mtok:.6}},{id:"gpt-4o-search-preview",name:"GPT-4o Search Preview",match:{equals:"gpt-4o-search-preview"},prices:{input_mtok:2.5,output_mtok:10}},{id:"gpt-4o:extended",name:"GPT-4o (extended)",match:{equals:"gpt-4o:extended"},prices:{input_mtok:6,output_mtok:18}},{id:"grok-2-1212",name:"Grok 2 1212",match:{equals:"grok-2-1212"},prices:{input_mtok:2,output_mtok:10}},{id:"grok-2-vision-1212",name:"Grok 2 Vision 1212",match:{equals:"grok-2-vision-1212"},prices:{input_mtok:2,output_mtok:10}},{id:"grok-3",name:"Grok 3",match:{or:[{equals:"grok-3"},{equals:"grok-3-beta"}]},prices:{input_mtok:3,cache_read_mtok:.75,output_mtok:15}},{id:"grok-3-mini",name:"Grok 3 Mini",match:{or:[{equals:"grok-3-mini"},{equals:"grok-3-mini-beta"}]},prices:{input_mtok:.3,cache_read_mtok:.075,output_mtok:.5}},{id:"grok-beta",name:"Grok Beta",match:{equals:"grok-beta"},prices:{input_mtok:5,output_mtok:15}},{id:"grok-vision-beta",name:"Grok Vision Beta",match:{equals:"grok-vision-beta"},prices:{input_mtok:5,output_mtok:15}},{id:"gryphe/mythomax-l2-13b",match:{equals:"gryphe/mythomax-l2-13b"},prices:{input_mtok:.065,output_mtok:.065}},{id:"hermes-2-pro-llama-3-8b",name:"Hermes 2 Pro - Llama-3 8B",match:{equals:"hermes-2-pro-llama-3-8b"},prices:{input_mtok:.025,output_mtok:.04}},{id:"hermes-3-llama-3.1-405b",name:"Hermes 3 405B Instruct",match:{equals:"hermes-3-llama-3.1-405b"},prices:{input_mtok:.7,output_mtok:.8}},{id:"hermes-3-llama-3.1-70b",name:"Hermes 3 70B Instruct",match:{equals:"hermes-3-llama-3.1-70b"},prices:{input_mtok:.12,output_mtok:.3}},{id:"huggingfaceh4/zephyr-7b-beta:free",match:{equals:"huggingfaceh4/zephyr-7b-beta:free"},prices:{}},{id:"infermatic/mn-inferor-12b",match:{equals:"infermatic/mn-inferor-12b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"inflection-3-pi",name:"Inflection 3 Pi",match:{equals:"inflection-3-pi"},prices:{input_mtok:2.5,output_mtok:10}},{id:"inflection-3-productivity",name:"Inflection 3 Productivity",match:{equals:"inflection-3-productivity"},prices:{input_mtok:2.5,output_mtok:10}},{id:"inflection/inflection-3-pi",match:{equals:"inflection/inflection-3-pi"},prices:{input_mtok:2.5,output_mtok:10}},{id:"inflection/inflection-3-productivity",match:{equals:"inflection/inflection-3-productivity"},prices:{input_mtok:2.5,output_mtok:10}},{id:"internvl3-14b:free",name:"InternVL3 14B (free)",match:{equals:"internvl3-14b:free"},prices:{}},{id:"internvl3-2b:free",name:"InternVL3 2B (free)",match:{equals:"internvl3-2b:free"},prices:{}},{id:"jamba-1.6-large",name:"Jamba 1.6 Large",match:{equals:"jamba-1.6-large"},prices:{input_mtok:2,output_mtok:8}},{id:"jamba-1.6-mini",name:"Jamba Mini 1.6",match:{equals:"jamba-1.6-mini"},prices:{input_mtok:.2,output_mtok:.4}},{id:"jondurbin/airoboros-l2-70b",match:{equals:"jondurbin/airoboros-l2-70b"},prices:{input_mtok:.5,output_mtok:.5}},{id:"kimi-dev-72b:free",name:"Kimi Dev 72b (free)",match:{equals:"kimi-dev-72b:free"},prices:{}},{id:"kimi-vl-a3b-thinking:free",name:"Kimi VL A3B Thinking (free)",match:{equals:"kimi-vl-a3b-thinking:free"},prices:{}},{id:"l3-euryale-70b",name:"Llama 3 Euryale 70B v2.1",match:{equals:"l3-euryale-70b"},prices:{input_mtok:1.48,output_mtok:1.48}},{id:"l3-lunaris-8b",name:"Llama 3 8B Lunaris",match:{equals:"l3-lunaris-8b"},prices:{input_mtok:.02,output_mtok:.05}},{id:"l3.1-euryale-70b",name:"Llama 3.1 Euryale 70B v2.2",match:{equals:"l3.1-euryale-70b"},prices:{input_mtok:.7,output_mtok:.8}},{id:"l3.3-euryale-70b",name:"Llama 3.3 Euryale 70B",match:{equals:"l3.3-euryale-70b"},prices:{input_mtok:.7,output_mtok:.8}},{id:"latitudegames/wayfarer-large-70b-llama-3.3",match:{equals:"latitudegames/wayfarer-large-70b-llama-3.3"},prices:{input_mtok:.8,output_mtok:.9}},{id:"lfm-3b",name:"LFM 3B",match:{equals:"lfm-3b"},prices:{input_mtok:.02,output_mtok:.02}},{id:"lfm-40b",name:"LFM 40B MoE",match:{equals:"lfm-40b"},prices:{input_mtok:.15,output_mtok:.15}},{id:"lfm-7b",name:"LFM 7B",match:{equals:"lfm-7b"},prices:{input_mtok:.01,output_mtok:.01}},{id:"liquid/lfm-3b",match:{equals:"liquid/lfm-3b"},prices:{input_mtok:.02,output_mtok:.02}},{id:"liquid/lfm-40b",match:{equals:"liquid/lfm-40b"},prices:{input_mtok:.15,output_mtok:.15}},{id:"liquid/lfm-7b",match:{equals:"liquid/lfm-7b"},prices:{input_mtok:.01,output_mtok:.01}},{id:"llama-3-70b-instruct",name:"Llama 3 70B Instruct",match:{equals:"llama-3-70b-instruct"},prices:{input_mtok:.3,output_mtok:.4}},{id:"llama-3-8b-instruct",name:"Llama 3 8B Instruct",match:{equals:"llama-3-8b-instruct"},prices:{input_mtok:.03,output_mtok:.06}},{id:"llama-3-lumimaid-70b",name:"Llama 3 Lumimaid 70B",match:{equals:"llama-3-lumimaid-70b"},prices:{input_mtok:4,output_mtok:6}},{id:"llama-3-lumimaid-8b",name:"Llama 3 Lumimaid 8B",match:{equals:"llama-3-lumimaid-8b"},prices:{input_mtok:.2,output_mtok:1.25}},{id:"llama-3.1-405b",name:"Llama 3.1 405B (base)",match:{equals:"llama-3.1-405b"},prices:{input_mtok:2,output_mtok:2}},{id:"llama-3.1-405b-instruct",name:"Llama 3.1 405B Instruct",match:{equals:"llama-3.1-405b-instruct"},prices:{input_mtok:.8,output_mtok:.8}},{id:"llama-3.1-70b-instruct",name:"Llama 3.1 70B Instruct",match:{equals:"llama-3.1-70b-instruct"},prices:{input_mtok:.1,output_mtok:.28}},{id:"llama-3.1-8b-instruct",name:"Llama 3.1 8B Instruct",match:{equals:"llama-3.1-8b-instruct"},prices:{input_mtok:.016,output_mtok:.029}},{id:"llama-3.1-8b-instruct:free",name:"Llama 3.1 8B Instruct (free)",match:{equals:"llama-3.1-8b-instruct:free"},prices:{}},{id:"llama-3.1-lumimaid-70b",name:"Lumimaid v0.2 70B",match:{equals:"llama-3.1-lumimaid-70b"},prices:{input_mtok:2.5,output_mtok:3}},{id:"llama-3.1-lumimaid-8b",name:"Lumimaid v0.2 8B",match:{equals:"llama-3.1-lumimaid-8b"},prices:{input_mtok:.2,output_mtok:1.25}},{id:"llama-3.1-nemotron-70b-instruct",name:"Llama 3.1 Nemotron 70B Instruct",match:{equals:"llama-3.1-nemotron-70b-instruct"},prices:{input_mtok:.12,output_mtok:.3}},{id:"llama-3.1-nemotron-ultra-253b-v1",name:"Llama 3.1 Nemotron Ultra 253B v1",match:{equals:"llama-3.1-nemotron-ultra-253b-v1"},prices:{input_mtok:.6,output_mtok:1.8}},{id:"llama-3.1-nemotron-ultra-253b-v1:free",name:"Llama 3.1 Nemotron Ultra 253B v1 (free)",match:{equals:"llama-3.1-nemotron-ultra-253b-v1:free"},prices:{}},{id:"llama-3.1-sonar-large-128k-online",name:"Llama 3.1 Sonar 70B Online",match:{equals:"llama-3.1-sonar-large-128k-online"},prices:{input_mtok:1,output_mtok:1}},{id:"llama-3.1-sonar-small-128k-online",name:"Llama 3.1 Sonar 8B Online",match:{equals:"llama-3.1-sonar-small-128k-online"},prices:{input_mtok:.2,output_mtok:.2}},{id:"llama-3.2-11b-vision-instruct",name:"Llama 3.2 11B Vision Instruct",match:{equals:"llama-3.2-11b-vision-instruct"},prices:{input_mtok:.049,output_mtok:.049}},{id:"llama-3.2-11b-vision-instruct:free",name:"Llama 3.2 11B Vision Instruct (free)",match:{equals:"llama-3.2-11b-vision-instruct:free"},prices:{}},{id:"llama-3.2-1b-instruct",name:"Llama 3.2 1B Instruct",match:{equals:"llama-3.2-1b-instruct"},prices:{input_mtok:.005,output_mtok:.01}},{id:"llama-3.2-1b-instruct:free",name:"Llama 3.2 1B Instruct (free)",match:{equals:"llama-3.2-1b-instruct:free"},prices:{}},{id:"llama-3.2-3b-instruct",name:"Llama 3.2 3B Instruct",match:{equals:"llama-3.2-3b-instruct"},prices:{input_mtok:.01,output_mtok:.02}},{id:"llama-3.2-3b-instruct:free",name:"Llama 3.2 3B Instruct (free)",match:{equals:"llama-3.2-3b-instruct:free"},prices:{}},{id:"llama-3.2-90b-vision-instruct",name:"Llama 3.2 90B Vision Instruct",match:{equals:"llama-3.2-90b-vision-instruct"},prices:{input_mtok:1.2,output_mtok:1.2}},{id:"llama-3.3-70b-instruct",name:"Llama 3.3 70B Instruct",match:{equals:"llama-3.3-70b-instruct"},prices:{input_mtok:.05,output_mtok:.24}},{id:"llama-3.3-70b-instruct:free",name:"Llama 3.3 70B Instruct (free)",match:{equals:"llama-3.3-70b-instruct:free"},prices:{}},{id:"llama-3.3-8b-instruct:free",name:"Llama 3.3 8B Instruct (free)",match:{equals:"llama-3.3-8b-instruct:free"},prices:{}},{id:"llama-3.3-nemotron-super-49b-v1",name:"Llama 3.3 Nemotron Super 49B v1",match:{equals:"llama-3.3-nemotron-super-49b-v1"},prices:{input_mtok:.13,output_mtok:.4}},{id:"llama-3.3-nemotron-super-49b-v1:free",name:"Llama 3.3 Nemotron Super 49B v1 (free)",match:{equals:"llama-3.3-nemotron-super-49b-v1:free"},prices:{}},{id:"llama-4-maverick",name:"Llama 4 Maverick",match:{equals:"llama-4-maverick"},prices:{input_mtok:.15,output_mtok:.6}},{id:"llama-4-maverick:free",name:"Llama 4 Maverick (free)",match:{equals:"llama-4-maverick:free"},prices:{}},{id:"llama-4-scout",name:"Llama 4 Scout",match:{equals:"llama-4-scout"},prices:{input_mtok:.08,output_mtok:.3}},{id:"llama-4-scout:free",name:"Llama 4 Scout (free)",match:{equals:"llama-4-scout:free"},prices:{}},{id:"llama-guard-2-8b",name:"LlamaGuard 2 8B",match:{equals:"llama-guard-2-8b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"llama-guard-3-8b",name:"Llama Guard 3 8B",match:{equals:"llama-guard-3-8b"},prices:{input_mtok:.02,output_mtok:.06}},{id:"llama-guard-4-12b",name:"Llama Guard 4 12B",match:{equals:"llama-guard-4-12b"},prices:{input_mtok:.05,output_mtok:.05}},{id:"llama3.1-typhoon2-70b-instruct",name:"Typhoon2 70B Instruct",match:{equals:"llama3.1-typhoon2-70b-instruct"},prices:{input_mtok:.88,output_mtok:.88}},{id:"llemma_7b",name:"Llemma 7b",match:{equals:"llemma_7b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"maestro-reasoning",name:"Maestro Reasoning",match:{equals:"maestro-reasoning"},prices:{input_mtok:.9,output_mtok:3.3}},{id:"magistral-medium-2506",name:"Magistral Medium 2506",match:{or:[{equals:"magistral-medium-2506"},{equals:"magistral-medium-2506:thinking"}]},prices:{input_mtok:2,output_mtok:5}},{id:"magistral-small-2506",name:"Magistral Small 2506",match:{equals:"magistral-small-2506"},prices:{input_mtok:.5,output_mtok:1.5}},{id:"magnum-72b",name:"Magnum 72B",match:{equals:"magnum-72b"},prices:{input_mtok:4,output_mtok:6}},{id:"magnum-v2-72b",name:"Magnum v2 72B",match:{equals:"magnum-v2-72b"},prices:{input_mtok:3,output_mtok:3}},{id:"magnum-v4-72b",name:"Magnum v4 72B",match:{equals:"magnum-v4-72b"},prices:{input_mtok:2.5,output_mtok:3}},{id:"mai-ds-r1:free",name:"MAI DS R1 (free)",match:{equals:"mai-ds-r1:free"},prices:{}},{id:"mancer/weaver",match:{equals:"mancer/weaver"},prices:{input_mtok:1.125,output_mtok:1.125}},{id:"mercury-coder-small-beta",name:"Mercury Coder Small Beta",match:{equals:"mercury-coder-small-beta"},prices:{input_mtok:.25,output_mtok:1}},{id:"meta-llama/llama-2-13b-chat",match:{equals:"meta-llama/llama-2-13b-chat"},prices:{input_mtok:.22,output_mtok:.22}},{id:"meta-llama/llama-2-70b-chat",match:{equals:"meta-llama/llama-2-70b-chat"},prices:{input_mtok:.9,output_mtok:.9}},{id:"meta-llama/llama-3-70b-instruct",match:{equals:"meta-llama/llama-3-70b-instruct"},prices:{input_mtok:.3,output_mtok:.4}},{id:"meta-llama/llama-3-8b-instruct",match:{equals:"meta-llama/llama-3-8b-instruct"},prices:{input_mtok:.03,output_mtok:.06}},{id:"meta-llama/llama-3.1-405b",match:{equals:"meta-llama/llama-3.1-405b"},prices:{input_mtok:2,output_mtok:2}},{id:"meta-llama/llama-3.1-405b-instruct",match:{equals:"meta-llama/llama-3.1-405b-instruct"},prices:{input_mtok:.8,output_mtok:.8}},{id:"meta-llama/llama-3.1-405b:free",match:{equals:"meta-llama/llama-3.1-405b:free"},prices:{}},{id:"meta-llama/llama-3.1-70b-instruct",match:{equals:"meta-llama/llama-3.1-70b-instruct"},prices:{input_mtok:.119,output_mtok:.39}},{id:"meta-llama/llama-3.1-8b-instruct",match:{equals:"meta-llama/llama-3.1-8b-instruct"},prices:{input_mtok:.02,output_mtok:.03}},{id:"meta-llama/llama-3.1-8b-instruct:free",match:{equals:"meta-llama/llama-3.1-8b-instruct:free"},prices:{}},{id:"meta-llama/llama-3.2-11b-vision-instruct",match:{equals:"meta-llama/llama-3.2-11b-vision-instruct"},prices:{input_mtok:.049,output_mtok:.049}},{id:"meta-llama/llama-3.2-11b-vision-instruct:free",match:{equals:"meta-llama/llama-3.2-11b-vision-instruct:free"},prices:{}},{id:"meta-llama/llama-3.2-1b-instruct",match:{equals:"meta-llama/llama-3.2-1b-instruct"},prices:{input_mtok:.01,output_mtok:.01}},{id:"meta-llama/llama-3.2-1b-instruct:free",match:{equals:"meta-llama/llama-3.2-1b-instruct:free"},prices:{}},{id:"meta-llama/llama-3.2-3b-instruct",match:{equals:"meta-llama/llama-3.2-3b-instruct"},prices:{input_mtok:.015,output_mtok:.025}},{id:"meta-llama/llama-3.2-3b-instruct:free",match:{equals:"meta-llama/llama-3.2-3b-instruct:free"},prices:{}},{id:"meta-llama/llama-3.2-90b-vision-instruct",match:{equals:"meta-llama/llama-3.2-90b-vision-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"meta-llama/llama-3.3-70b-instruct",match:{equals:"meta-llama/llama-3.3-70b-instruct"},prices:{input_mtok:.1,output_mtok:.25}},{id:"meta-llama/llama-3.3-70b-instruct:free",match:{equals:"meta-llama/llama-3.3-70b-instruct:free"},prices:{}},{id:"meta-llama/llama-4-maverick",match:{equals:"meta-llama/llama-4-maverick"},prices:{input_mtok:.17,output_mtok:.85}},{id:"meta-llama/llama-4-maverick:free",match:{equals:"meta-llama/llama-4-maverick:free"},prices:{}},{id:"meta-llama/llama-4-scout",match:{equals:"meta-llama/llama-4-scout"},prices:{input_mtok:.08,output_mtok:.3}},{id:"meta-llama/llama-4-scout:free",match:{equals:"meta-llama/llama-4-scout:free"},prices:{}},{id:"meta-llama/llama-guard-2-8b",match:{equals:"meta-llama/llama-guard-2-8b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"meta-llama/llama-guard-3-8b",match:{equals:"meta-llama/llama-guard-3-8b"},prices:{input_mtok:.1,output_mtok:.1}},{id:"microsoft/phi-3-medium-128k-instruct",match:{equals:"microsoft/phi-3-medium-128k-instruct"},prices:{input_mtok:1,output_mtok:1}},{id:"microsoft/phi-3-mini-128k-instruct",match:{equals:"microsoft/phi-3-mini-128k-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"microsoft/phi-3.5-mini-128k-instruct",match:{equals:"microsoft/phi-3.5-mini-128k-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"microsoft/phi-4",match:{equals:"microsoft/phi-4"},prices:{input_mtok:.07,output_mtok:.14}},{id:"microsoft/phi-4-multimodal-instruct",match:{equals:"microsoft/phi-4-multimodal-instruct"},prices:{input_mtok:.05,output_mtok:.1}},{id:"microsoft/wizardlm-2-7b",match:{equals:"microsoft/wizardlm-2-7b"},prices:{input_mtok:.07,output_mtok:.07}},{id:"microsoft/wizardlm-2-8x22b",match:{equals:"microsoft/wizardlm-2-8x22b"},prices:{input_mtok:.5,output_mtok:.5}},{id:"midnight-rose-70b",name:"Midnight Rose 70B",match:{equals:"midnight-rose-70b"},prices:{input_mtok:.8,output_mtok:.8}},{id:"minimax-01",name:"MiniMax-01",match:{equals:"minimax-01"},prices:{input_mtok:.2,output_mtok:1.1}},{id:"minimax-m1",name:"MiniMax M1",match:{equals:"minimax-m1"},prices:{input_mtok:.3,output_mtok:1.65}},{id:"minimax-m1:extended",name:"MiniMax M1 (extended)",match:{equals:"minimax-m1:extended"},prices:{input_mtok:.55,output_mtok:2.2}},{id:"minimax/minimax-01",match:{equals:"minimax/minimax-01"},prices:{input_mtok:.2,output_mtok:1.1}},{id:"ministral-3b",name:"Ministral 3B",match:{equals:"ministral-3b"},prices:{input_mtok:.04,output_mtok:.04}},{id:"ministral-8b",name:"Ministral 8B",match:{equals:"ministral-8b"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistral-7b-instruct",name:"Mistral 7B Instruct",match:{or:[{equals:"mistral-7b-instruct"},{equals:"mistral-7b-instruct-v0.3"}]},prices:{input_mtok:.028,output_mtok:.054}},{id:"mistral-7b-instruct-v0.1",name:"Mistral 7B Instruct v0.1",match:{equals:"mistral-7b-instruct-v0.1"},prices:{input_mtok:.11,output_mtok:.19}},{id:"mistral-7b-instruct-v0.2",name:"Mistral 7B Instruct v0.2",match:{equals:"mistral-7b-instruct-v0.2"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistral-7b-instruct:free",name:"Mistral 7B Instruct (free)",match:{equals:"mistral-7b-instruct:free"},prices:{}},{id:"mistral-large",name:"Mistral Large",match:{or:[{equals:"mistral-large"},{equals:"mistral-large-2407"},{equals:"mistral-large-2411"}]},prices:{input_mtok:2,output_mtok:6}},{id:"mistral-medium",name:"Mistral Medium",match:{equals:"mistral-medium"},prices:{input_mtok:2.75,output_mtok:8.1}},{id:"mistral-medium-3",name:"Mistral Medium 3",match:{equals:"mistral-medium-3"},prices:{input_mtok:.4,output_mtok:2}},{id:"mistral-nemo",name:"Mistral Nemo",match:{equals:"mistral-nemo"},prices:{input_mtok:.01,output_mtok:.019}},{id:"mistral-nemo:free",name:"Mistral Nemo (free)",match:{equals:"mistral-nemo:free"},prices:{}},{id:"mistral-saba",name:"Saba",match:{equals:"mistral-saba"},prices:{input_mtok:.2,output_mtok:.6}},{id:"mistral-small",name:"Mistral Small",match:{equals:"mistral-small"},prices:{input_mtok:.2,output_mtok:.6}},{id:"mistral-small-24b-instruct-2501",name:"Mistral Small 3",match:{equals:"mistral-small-24b-instruct-2501"},prices:{input_mtok:.05,output_mtok:.09}},{id:"mistral-small-24b-instruct-2501:free",name:"Mistral Small 3 (free)",match:{equals:"mistral-small-24b-instruct-2501:free"},prices:{}},{id:"mistral-small-3.1-24b-instruct",name:"Mistral Small 3.1 24B",match:{equals:"mistral-small-3.1-24b-instruct"},prices:{input_mtok:.05,output_mtok:.15}},{id:"mistral-small-3.1-24b-instruct:free",name:"Mistral Small 3.1 24B (free)",match:{equals:"mistral-small-3.1-24b-instruct:free"},prices:{}},{id:"mistral-small-3.2-24b-instruct:free",name:"Mistral Small 3.2 24B (free)",match:{equals:"mistral-small-3.2-24b-instruct:free"},prices:{}},{id:"mistral-tiny",name:"Mistral Tiny",match:{equals:"mistral-tiny"},prices:{input_mtok:.25,output_mtok:.25}},{id:"mistral/ministral-8b",match:{equals:"mistral/ministral-8b"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistralai/codestral-2501",match:{equals:"mistralai/codestral-2501"},prices:{input_mtok:.3,output_mtok:.9}},{id:"mistralai/codestral-mamba",match:{equals:"mistralai/codestral-mamba"},prices:{input_mtok:.25,output_mtok:.25}},{id:"mistralai/ministral-3b",match:{equals:"mistralai/ministral-3b"},prices:{input_mtok:.04,output_mtok:.04}},{id:"mistralai/ministral-8b",match:{equals:"mistralai/ministral-8b"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistralai/mistral-7b-instruct",match:{or:[{equals:"mistralai/mistral-7b-instruct"},{equals:"mistralai/mistral-7b-instruct-v0.3"}]},prices:{input_mtok:.029,output_mtok:.059}},{id:"mistralai/mistral-7b-instruct-v0.1",match:{equals:"mistralai/mistral-7b-instruct-v0.1"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistralai/mistral-7b-instruct-v0.2",match:{equals:"mistralai/mistral-7b-instruct-v0.2"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistralai/mistral-7b-instruct:free",match:{equals:"mistralai/mistral-7b-instruct:free"},prices:{}},{id:"mistralai/mistral-large",match:{or:[{equals:"mistralai/mistral-large"},{equals:"mistralai/mistral-large-2407"},{equals:"mistralai/mistral-large-2411"}]},prices:{input_mtok:2,output_mtok:6}},{id:"mistralai/mistral-medium",match:{equals:"mistralai/mistral-medium"},prices:{input_mtok:2.75,output_mtok:8.1}},{id:"mistralai/mistral-nemo",match:{equals:"mistralai/mistral-nemo"},prices:{input_mtok:.035,output_mtok:.08}},{id:"mistralai/mistral-nemo:free",match:{equals:"mistralai/mistral-nemo:free"},prices:{}},{id:"mistralai/mistral-saba",match:{equals:"mistralai/mistral-saba"},prices:{input_mtok:.2,output_mtok:.6}},{id:"mistralai/mistral-small",match:{equals:"mistralai/mistral-small"},prices:{input_mtok:.2,output_mtok:.6}},{id:"mistralai/mistral-small-24b-instruct-2501",match:{equals:"mistralai/mistral-small-24b-instruct-2501"},prices:{input_mtok:.07,output_mtok:.14}},{id:"mistralai/mistral-small-24b-instruct-2501:free",match:{equals:"mistralai/mistral-small-24b-instruct-2501:free"},prices:{}},{id:"mistralai/mistral-small-3.1-24b-instruct",match:{equals:"mistralai/mistral-small-3.1-24b-instruct"},prices:{input_mtok:.1,output_mtok:.3}},{id:"mistralai/mistral-small-3.1-24b-instruct:free",match:{equals:"mistralai/mistral-small-3.1-24b-instruct:free"},prices:{}},{id:"mistralai/mistral-tiny",match:{equals:"mistralai/mistral-tiny"},prices:{input_mtok:.25,output_mtok:.25}},{id:"mistralai/mixtral-8x22b-instruct",match:{equals:"mistralai/mixtral-8x22b-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"mistralai/mixtral-8x7b-instruct",match:{equals:"mistralai/mixtral-8x7b-instruct"},prices:{input_mtok:.24,output_mtok:.24}},{id:"mistralai/pixtral-12b",match:{equals:"mistralai/pixtral-12b"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistralai/pixtral-large-2411",match:{equals:"mistralai/pixtral-large-2411"},prices:{input_mtok:2,output_mtok:6}},{id:"mixtral-8x22b-instruct",name:"Mixtral 8x22B Instruct",match:{equals:"mixtral-8x22b-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"mixtral-8x7b-instruct",name:"Mixtral 8x7B Instruct",match:{equals:"mixtral-8x7b-instruct"},prices:{input_mtok:.08,output_mtok:.24}},{id:"mn-celeste-12b",name:"Mistral Nemo 12B Celeste",match:{equals:"mn-celeste-12b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"mn-inferor-12b",name:"Mistral Nemo Inferor 12B",match:{equals:"mn-inferor-12b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"mn-starcannon-12b",name:"Starcannon 12B",match:{equals:"mn-starcannon-12b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"moonshotai/kimi-k2.5",name:"Kimi K2.5",match:{equals:"moonshotai/kimi-k2.5"},prices:{input_mtok:.6,output_mtok:3}},{id:"moonshotai/kimi-vl-a3b-thinking:free",match:{equals:"moonshotai/kimi-vl-a3b-thinking:free"},prices:{}},{id:"moonshotai/moonlight-16b-a3b-instruct:free",match:{equals:"moonshotai/moonlight-16b-a3b-instruct:free"},prices:{}},{id:"mythalion-13b",name:"Mythalion 13B",match:{equals:"mythalion-13b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"mythomax-l2-13b",name:"MythoMax 13B",match:{equals:"mythomax-l2-13b"},prices:{input_mtok:.065,output_mtok:.065}},{id:"neversleep/llama-3-lumimaid-70b",match:{equals:"neversleep/llama-3-lumimaid-70b"},prices:{input_mtok:3.375,output_mtok:4.5}},{id:"neversleep/llama-3-lumimaid-8b",match:{or:[{equals:"neversleep/llama-3-lumimaid-8b"},{equals:"neversleep/llama-3-lumimaid-8b:extended"}]},prices:{input_mtok:.09375,output_mtok:.75}},{id:"neversleep/llama-3.1-lumimaid-70b",match:{equals:"neversleep/llama-3.1-lumimaid-70b"},prices:{input_mtok:1.5,output_mtok:2.25}},{id:"neversleep/llama-3.1-lumimaid-8b",match:{equals:"neversleep/llama-3.1-lumimaid-8b"},prices:{input_mtok:.09375,output_mtok:.75}},{id:"neversleep/noromaid-20b",match:{equals:"neversleep/noromaid-20b"},prices:{input_mtok:.75,output_mtok:1.5}},{id:"noromaid-20b",name:"Noromaid 20B",match:{equals:"noromaid-20b"},prices:{input_mtok:1.25,output_mtok:2}},{id:"nothingiisreal/mn-celeste-12b",match:{equals:"nothingiisreal/mn-celeste-12b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"nous-hermes-2-mixtral-8x7b-dpo",name:"Hermes 2 Mixtral 8x7B DPO",match:{equals:"nous-hermes-2-mixtral-8x7b-dpo"},prices:{input_mtok:.6,output_mtok:.6}},{id:"nousresearch/deephermes-3-llama-3-8b-preview:free",match:{equals:"nousresearch/deephermes-3-llama-3-8b-preview:free"},prices:{}},{id:"nousresearch/hermes-2-pro-llama-3-8b",match:{equals:"nousresearch/hermes-2-pro-llama-3-8b"},prices:{input_mtok:.025,output_mtok:.04}},{id:"nousresearch/hermes-3-llama-3.1-405b",match:{equals:"nousresearch/hermes-3-llama-3.1-405b"},prices:{input_mtok:.8,output_mtok:.8}},{id:"nousresearch/hermes-3-llama-3.1-70b",match:{equals:"nousresearch/hermes-3-llama-3.1-70b"},prices:{input_mtok:.12,output_mtok:.3}},{id:"nousresearch/nous-hermes-2-mixtral-8x7b-dpo",match:{equals:"nousresearch/nous-hermes-2-mixtral-8x7b-dpo"},prices:{input_mtok:.6,output_mtok:.6}},{id:"nousresearch/nous-hermes-llama2-13b",match:{equals:"nousresearch/nous-hermes-llama2-13b"},prices:{input_mtok:.18,output_mtok:.18}},{id:"nova-lite-v1",name:"Nova Lite 1.0",match:{equals:"nova-lite-v1"},prices:{input_mtok:.06,output_mtok:.24}},{id:"nova-micro-v1",name:"Nova Micro 1.0",match:{equals:"nova-micro-v1"},prices:{input_mtok:.035,output_mtok:.14}},{id:"nova-pro-v1",name:"Nova Pro 1.0",match:{equals:"nova-pro-v1"},prices:{input_mtok:.8,output_mtok:3.2}},{id:"nvidia/llama-3.1-nemotron-70b-instruct",match:{equals:"nvidia/llama-3.1-nemotron-70b-instruct"},prices:{input_mtok:.12,output_mtok:.3}},{id:"nvidia/llama-3.1-nemotron-70b-instruct:free",match:{equals:"nvidia/llama-3.1-nemotron-70b-instruct:free"},prices:{}},{id:"nvidia/llama-3.1-nemotron-nano-8b-v1:free",match:{equals:"nvidia/llama-3.1-nemotron-nano-8b-v1:free"},prices:{}},{id:"nvidia/llama-3.1-nemotron-ultra-253b-v1:free",match:{equals:"nvidia/llama-3.1-nemotron-ultra-253b-v1:free"},prices:{}},{id:"nvidia/llama-3.3-nemotron-super-49b-v1:free",match:{equals:"nvidia/llama-3.3-nemotron-super-49b-v1:free"},prices:{}},{id:"o1",name:"o1",match:{or:[{equals:"o1"},{equals:"o1-preview"},{equals:"o1-preview-2024-09-12"}]},prices:{input_mtok:15,cache_read_mtok:7.5,output_mtok:60}},{id:"o1-mini",name:"o1-mini",match:{or:[{equals:"o1-mini"},{equals:"o1-mini-2024-09-12"}]},prices:{input_mtok:1.1,cache_read_mtok:.55,output_mtok:4.4}},{id:"o1-pro",name:"o1-pro",match:{equals:"o1-pro"},prices:{input_mtok:150,output_mtok:600}},{id:"o3",name:"o3",match:{equals:"o3"},prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}},{id:"o3-mini",name:"o3 Mini",match:{or:[{equals:"o3-mini"},{equals:"o3-mini-high"}]},prices:{input_mtok:1.1,cache_read_mtok:.55,output_mtok:4.4}},{id:"o3-pro",name:"o3 Pro",match:{equals:"o3-pro"},prices:{input_mtok:20,output_mtok:80}},{id:"o4-mini",name:"o4 Mini",match:{or:[{equals:"o4-mini"},{equals:"o4-mini-high"}]},prices:{input_mtok:1.1,cache_read_mtok:.275,output_mtok:4.4}},{id:"open-r1/olympiccoder-32b:free",match:{equals:"open-r1/olympiccoder-32b:free"},prices:{}},{id:"open-r1/olympiccoder-7b:free",match:{equals:"open-r1/olympiccoder-7b:free"},prices:{}},{id:"openai/chatgpt-4o-latest",match:{equals:"openai/chatgpt-4o-latest"},prices:{input_mtok:5,output_mtok:15}},{id:"openai/codex-mini",match:{equals:"openai/codex-mini"},prices:{input_mtok:1.5,cache_read_mtok:.375,output_mtok:6}},{id:"openai/gpt-3.5-turbo",match:{or:[{equals:"openai/gpt-3.5-turbo"},{equals:"openai/gpt-3.5-turbo-0125"}]},prices:{input_mtok:.5,output_mtok:1.5}},{id:"openai/gpt-3.5-turbo-0613",match:{equals:"openai/gpt-3.5-turbo-0613"},prices:{input_mtok:1,output_mtok:2}},{id:"openai/gpt-3.5-turbo-1106",match:{equals:"openai/gpt-3.5-turbo-1106"},prices:{input_mtok:1,output_mtok:2}},{id:"openai/gpt-3.5-turbo-16k",match:{equals:"openai/gpt-3.5-turbo-16k"},prices:{input_mtok:3,output_mtok:4}},{id:"openai/gpt-3.5-turbo-instruct",match:{equals:"openai/gpt-3.5-turbo-instruct"},prices:{input_mtok:1.5,output_mtok:2}},{id:"openai/gpt-4",match:{or:[{equals:"openai/gpt-4"},{equals:"openai/gpt-4-0314"}]},prices:{input_mtok:30,output_mtok:60}},{id:"openai/gpt-4-1106-preview",match:{equals:"openai/gpt-4-1106-preview"},prices:{input_mtok:10,output_mtok:30}},{id:"openai/gpt-4-32k",match:{or:[{equals:"openai/gpt-4-32k"},{equals:"openai/gpt-4-32k-0314"}]},prices:{input_mtok:60,output_mtok:120}},{id:"openai/gpt-4-turbo",match:{or:[{equals:"openai/gpt-4-turbo"},{equals:"openai/gpt-4-turbo-preview"}]},prices:{input_mtok:10,output_mtok:30}},{id:"openai/gpt-4.1",match:{equals:"openai/gpt-4.1"},prices:{input_mtok:2,output_mtok:8}},{id:"openai/gpt-4.1-mini",match:{equals:"openai/gpt-4.1-mini"},prices:{input_mtok:.4,output_mtok:1.6}},{id:"openai/gpt-4.1-nano",match:{equals:"openai/gpt-4.1-nano"},prices:{input_mtok:.1,output_mtok:.4}},{id:"openai/gpt-4.5-preview",match:{equals:"openai/gpt-4.5-preview"},prices:{input_mtok:75,output_mtok:150}},{id:"openai/gpt-4o",match:{or:[{equals:"openai/gpt-4o"},{equals:"openai/gpt-4o-2024-08-06"},{equals:"openai/gpt-4o-2024-11-20"},{equals:"openai/gpt-4o-search-preview"},{equals:"openai/gpt-4o-audio-preview"}]},prices:{input_mtok:2.5,output_mtok:10}},{id:"openai/gpt-4o-2024-05-13",match:{equals:"openai/gpt-4o-2024-05-13"},prices:{input_mtok:5,output_mtok:15}},{id:"openai/gpt-4o-mini",match:{or:[{equals:"openai/gpt-4o-mini"},{equals:"openai/gpt-4o-mini-2024-07-18"},{equals:"openai/gpt-4o-mini-search-preview"}]},prices:{input_mtok:.15,output_mtok:.6}},{id:"openai/gpt-4o:extended",match:{equals:"openai/gpt-4o:extended"},prices:{input_mtok:6,output_mtok:18}},{id:"openai/gpt-5",match:{or:[{equals:"openai/gpt-5"},{equals:"openai/gpt-5-chat"},{equals:"openai/gpt-5-codex"},{equals:"openai/gpt-5.1"},{equals:"openai/gpt-5.1-chat"},{equals:"openai/gpt-5.1-codex"}]},prices:{input_mtok:1.25,cache_read_mtok:.125,output_mtok:10}},{id:"openai/gpt-5-image",match:{equals:"openai/gpt-5-image"},price_comments:"Image pricing at $0.01/1k images not represented in standard schema",prices:{input_mtok:10,cache_read_mtok:1.25,output_mtok:10}},{id:"openai/gpt-5-image-mini",match:{equals:"openai/gpt-5-image-mini"},price_comments:"Image pricing at $0.0025/1k images not represented in standard schema",prices:{input_mtok:2.5,cache_read_mtok:.25,output_mtok:2}},{id:"openai/gpt-5-mini",match:{equals:"openai/gpt-5-mini"},prices:{input_mtok:.25,cache_read_mtok:.025,output_mtok:2}},{id:"openai/gpt-5-nano",match:{equals:"openai/gpt-5-nano"},prices:{input_mtok:.05,cache_read_mtok:.005,output_mtok:.4}},{id:"openai/gpt-5-pro",match:{equals:"openai/gpt-5-pro"},prices:{input_mtok:15,output_mtok:120}},{id:"openai/gpt-5.1-codex-mini",match:{equals:"openai/gpt-5.1-codex-mini"},prices:{input_mtok:.25,cache_read_mtok:.025,output_mtok:2}},{id:"openai/gpt-oss-120b",match:{or:[{equals:"openai/gpt-oss-120b"},{equals:"openai/gpt-oss-120b:exacto"}]},prices:{input_mtok:.04,output_mtok:.2}},{id:"openai/gpt-oss-20b",match:{equals:"openai/gpt-oss-20b"},prices:{input_mtok:.03,output_mtok:.14}},{id:"openai/gpt-oss-20b:free",match:{equals:"openai/gpt-oss-20b:free"},prices:{}},{id:"openai/gpt-oss-safeguard-20b",match:{equals:"openai/gpt-oss-safeguard-20b"},prices:{input_mtok:.075,cache_read_mtok:.037,output_mtok:.3}},{id:"openai/o1",match:{or:[{equals:"openai/o1"},{equals:"openai/o1-preview"},{equals:"openai/o1-preview-2024-09-12"}]},prices:{input_mtok:15,output_mtok:60}},{id:"openai/o1-mini",match:{or:[{equals:"openai/o1-mini"},{equals:"openai/o1-mini-2024-09-12"}]},prices:{input_mtok:1.1,output_mtok:4.4}},{id:"openai/o1-pro",match:{equals:"openai/o1-pro"},prices:{input_mtok:150,output_mtok:600}},{id:"openai/o3",match:{equals:"openai/o3"},prices:{input_mtok:10,output_mtok:40}},{id:"openai/o3-deep-research",match:{equals:"openai/o3-deep-research"},price_comments:"Image pricing at $7.65/1k images not represented in standard schema",prices:{input_mtok:10,cache_read_mtok:2.5,output_mtok:40}},{id:"openai/o3-mini",match:{or:[{equals:"openai/o3-mini"},{equals:"openai/o3-mini-high"}]},prices:{input_mtok:1.1,output_mtok:4.4}},{id:"openai/o3-pro",match:{equals:"openai/o3-pro"},price_comments:"Image pricing at $15.30/1k images not represented in standard schema",prices:{input_mtok:20,output_mtok:80}},{id:"openai/o4-mini",match:{or:[{equals:"openai/o4-mini"},{equals:"openai/o4-mini-high"}]},prices:{input_mtok:1.1,output_mtok:4.4}},{id:"openai/o4-mini-deep-research",match:{equals:"openai/o4-mini-deep-research"},price_comments:"Image pricing at $1.53/1k images not represented in standard schema",prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}},{id:"openchat/openchat-7b",match:{equals:"openchat/openchat-7b"},prices:{input_mtok:.07,output_mtok:.07}},{id:"openhands-lm-32b-v0.1",name:"OpenHands LM 32B V0.1",match:{equals:"openhands-lm-32b-v0.1"},prices:{input_mtok:2.6,output_mtok:3.4}},{id:"perplexity/llama-3.1-sonar-large-128k-online",match:{equals:"perplexity/llama-3.1-sonar-large-128k-online"},prices:{input_mtok:1,output_mtok:1}},{id:"perplexity/llama-3.1-sonar-small-128k-online",match:{equals:"perplexity/llama-3.1-sonar-small-128k-online"},prices:{input_mtok:.2,output_mtok:.2}},{id:"perplexity/r1-1776",match:{equals:"perplexity/r1-1776"},prices:{input_mtok:2,output_mtok:8}},{id:"perplexity/sonar",match:{equals:"perplexity/sonar"},prices:{input_mtok:1,output_mtok:1}},{id:"perplexity/sonar-deep-research",match:{equals:"perplexity/sonar-deep-research"},prices:{input_mtok:2,output_mtok:8}},{id:"perplexity/sonar-pro",match:{equals:"perplexity/sonar-pro"},prices:{input_mtok:3,output_mtok:15}},{id:"perplexity/sonar-reasoning",match:{equals:"perplexity/sonar-reasoning"},prices:{input_mtok:1,output_mtok:5}},{id:"perplexity/sonar-reasoning-pro",match:{equals:"perplexity/sonar-reasoning-pro"},prices:{input_mtok:2,output_mtok:8}},{id:"phi-3-medium-128k-instruct",name:"Phi-3 Medium 128K Instruct",match:{equals:"phi-3-medium-128k-instruct"},prices:{input_mtok:1,output_mtok:1}},{id:"phi-3-mini-128k-instruct",name:"Phi-3 Mini 128K Instruct",match:{equals:"phi-3-mini-128k-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"phi-3.5-mini-128k-instruct",name:"Phi-3.5 Mini 128K Instruct",match:{equals:"phi-3.5-mini-128k-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"phi-4",name:"Phi 4",match:{equals:"phi-4"},prices:{input_mtok:.07,output_mtok:.14}},{id:"phi-4-multimodal-instruct",name:"Phi 4 Multimodal Instruct",match:{equals:"phi-4-multimodal-instruct"},prices:{input_mtok:.05,output_mtok:.1}},{id:"phi-4-reasoning-plus",name:"Phi 4 Reasoning Plus",match:{equals:"phi-4-reasoning-plus"},prices:{input_mtok:.07,output_mtok:.35}},{id:"phi-4-reasoning-plus:free",name:"Phi 4 Reasoning Plus (free)",match:{equals:"phi-4-reasoning-plus:free"},prices:{}},{id:"phi-4-reasoning:free",name:"Phi 4 Reasoning (free)",match:{equals:"phi-4-reasoning:free"},prices:{}},{id:"pixtral-12b",name:"Pixtral 12B",match:{equals:"pixtral-12b"},prices:{input_mtok:.1,output_mtok:.1}},{id:"pixtral-large-2411",name:"Pixtral Large 2411",match:{equals:"pixtral-large-2411"},prices:{input_mtok:2,output_mtok:6}},{id:"pygmalionai/mythalion-13b",match:{equals:"pygmalionai/mythalion-13b"},prices:{input_mtok:.5625,output_mtok:1.125}},{id:"qwen-2-72b-instruct",name:"Qwen 2 72B Instruct",match:{equals:"qwen-2-72b-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"qwen-2.5-72b-instruct",name:"Qwen2.5 72B Instruct",match:{equals:"qwen-2.5-72b-instruct"},prices:{input_mtok:.12,output_mtok:.39}},{id:"qwen-2.5-72b-instruct:free",name:"Qwen2.5 72B Instruct (free)",match:{equals:"qwen-2.5-72b-instruct:free"},prices:{}},{id:"qwen-2.5-7b-instruct",name:"Qwen2.5 7B Instruct",match:{equals:"qwen-2.5-7b-instruct"},prices:{input_mtok:.04,output_mtok:.1}},{id:"qwen-2.5-coder-32b-instruct",name:"Qwen2.5 Coder 32B Instruct",match:{equals:"qwen-2.5-coder-32b-instruct"},prices:{input_mtok:.06,output_mtok:.15}},{id:"qwen-2.5-coder-32b-instruct:free",name:"Qwen2.5 Coder 32B Instruct (free)",match:{equals:"qwen-2.5-coder-32b-instruct:free"},prices:{}},{id:"qwen-2.5-vl-7b-instruct",name:"Qwen2.5-VL 7B Instruct",match:{equals:"qwen-2.5-vl-7b-instruct"},prices:{input_mtok:.2,output_mtok:.2}},{id:"qwen-max",name:"Qwen-Max",match:{equals:"qwen-max"},prices:{input_mtok:1.6,cache_read_mtok:.64,output_mtok:6.4}},{id:"qwen-plus",name:"Qwen-Plus",match:{equals:"qwen-plus"},prices:{input_mtok:.4,cache_read_mtok:.16,output_mtok:1.2}},{id:"qwen-turbo",name:"Qwen-Turbo",match:{equals:"qwen-turbo"},prices:{input_mtok:.05,cache_read_mtok:.02,output_mtok:.2}},{id:"qwen-vl-max",name:"Qwen VL Max",match:{equals:"qwen-vl-max"},prices:{input_mtok:.8,output_mtok:3.2}},{id:"qwen-vl-plus",name:"Qwen VL Plus",match:{equals:"qwen-vl-plus"},prices:{input_mtok:.21,output_mtok:.63}},{id:"qwen/qwen-2-72b-instruct",match:{equals:"qwen/qwen-2-72b-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"qwen/qwen-2.5-72b-instruct",match:{equals:"qwen/qwen-2.5-72b-instruct"},prices:{input_mtok:.12,output_mtok:.39}},{id:"qwen/qwen-2.5-72b-instruct:free",match:{equals:"qwen/qwen-2.5-72b-instruct:free"},prices:{}},{id:"qwen/qwen-2.5-7b-instruct",match:{equals:"qwen/qwen-2.5-7b-instruct"},prices:{input_mtok:.05,output_mtok:.1}},{id:"qwen/qwen-2.5-7b-instruct:free",match:{equals:"qwen/qwen-2.5-7b-instruct:free"},prices:{}},{id:"qwen/qwen-2.5-coder-32b-instruct",match:{equals:"qwen/qwen-2.5-coder-32b-instruct"},prices:{input_mtok:.07,output_mtok:.15}},{id:"qwen/qwen-2.5-coder-32b-instruct:free",match:{equals:"qwen/qwen-2.5-coder-32b-instruct:free"},prices:{}},{id:"qwen/qwen-2.5-vl-72b-instruct",match:{equals:"qwen/qwen-2.5-vl-72b-instruct"},prices:{input_mtok:.6,output_mtok:.6}},{id:"qwen/qwen-2.5-vl-7b-instruct",match:{equals:"qwen/qwen-2.5-vl-7b-instruct"},prices:{input_mtok:.2,output_mtok:.2}},{id:"qwen/qwen-2.5-vl-7b-instruct:free",match:{equals:"qwen/qwen-2.5-vl-7b-instruct:free"},prices:{}},{id:"qwen/qwen-max",match:{equals:"qwen/qwen-max"},prices:{input_mtok:1.6,output_mtok:6.4}},{id:"qwen/qwen-plus",match:{equals:"qwen/qwen-plus"},prices:{input_mtok:.4,output_mtok:1.2}},{id:"qwen/qwen-turbo",match:{equals:"qwen/qwen-turbo"},prices:{input_mtok:.05,output_mtok:.2}},{id:"qwen/qwen-vl-max",match:{equals:"qwen/qwen-vl-max"},prices:{input_mtok:.8,output_mtok:3.2}},{id:"qwen/qwen-vl-plus",match:{equals:"qwen/qwen-vl-plus"},prices:{input_mtok:.21,output_mtok:.63}},{id:"qwen/qwen2.5-coder-7b-instruct",match:{equals:"qwen/qwen2.5-coder-7b-instruct"},prices:{input_mtok:.2,output_mtok:.2}},{id:"qwen/qwen2.5-vl-32b-instruct",match:{equals:"qwen/qwen2.5-vl-32b-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"qwen/qwen2.5-vl-32b-instruct:free",match:{equals:"qwen/qwen2.5-vl-32b-instruct:free"},prices:{}},{id:"qwen/qwen2.5-vl-3b-instruct:free",match:{equals:"qwen/qwen2.5-vl-3b-instruct:free"},prices:{}},{id:"qwen/qwen2.5-vl-72b-instruct",match:{equals:"qwen/qwen2.5-vl-72b-instruct"},prices:{input_mtok:.7,output_mtok:.7}},{id:"qwen/qwen2.5-vl-72b-instruct:free",match:{equals:"qwen/qwen2.5-vl-72b-instruct:free"},prices:{}},{id:"qwen/qwen3-max",name:"Qwen 3 Max",match:{or:[{equals:"qwen/qwen3-max"},{equals:"qwen/qwen3-max-thinking"}]},prices:{input_mtok:1.2,output_mtok:6}},{id:"qwen/qwq-32b",match:{equals:"qwen/qwq-32b"},prices:{input_mtok:.15,output_mtok:.2}},{id:"qwen/qwq-32b-preview",match:{equals:"qwen/qwq-32b-preview"},prices:{input_mtok:.2,output_mtok:.2}},{id:"qwen/qwq-32b-preview:free",match:{equals:"qwen/qwq-32b-preview:free"},prices:{}},{id:"qwen/qwq-32b:free",match:{equals:"qwen/qwq-32b:free"},prices:{}},{id:"qwen2.5-vl-32b-instruct",name:"Qwen2.5 VL 32B Instruct",match:{equals:"qwen2.5-vl-32b-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"qwen2.5-vl-32b-instruct:free",name:"Qwen2.5 VL 32B Instruct (free)",match:{equals:"qwen2.5-vl-32b-instruct:free"},prices:{}},{id:"qwen2.5-vl-72b-instruct",name:"Qwen2.5 VL 72B Instruct",match:{equals:"qwen2.5-vl-72b-instruct"},prices:{input_mtok:.25,output_mtok:.75}},{id:"qwen2.5-vl-72b-instruct:free",name:"Qwen2.5 VL 72B Instruct (free)",match:{equals:"qwen2.5-vl-72b-instruct:free"},prices:{}},{id:"qwen3-14b",name:"Qwen3 14B",match:{equals:"qwen3-14b"},prices:{input_mtok:.06,output_mtok:.24}},{id:"qwen3-14b:free",name:"Qwen3 14B (free)",match:{equals:"qwen3-14b:free"},prices:{}},{id:"qwen3-235b-a22b",name:"Qwen3 235B A22B",match:{equals:"qwen3-235b-a22b"},prices:{input_mtok:.13,output_mtok:.6}},{id:"qwen3-235b-a22b:free",name:"Qwen3 235B A22B (free)",match:{equals:"qwen3-235b-a22b:free"},prices:{}},{id:"qwen3-30b-a3b",name:"Qwen3 30B A3B",match:{equals:"qwen3-30b-a3b"},prices:{input_mtok:.08,output_mtok:.29}},{id:"qwen3-30b-a3b:free",name:"Qwen3 30B A3B (free)",match:{equals:"qwen3-30b-a3b:free"},prices:{}},{id:"qwen3-32b",name:"Qwen3 32B",match:{equals:"qwen3-32b"},prices:{input_mtok:.1,output_mtok:.3}},{id:"qwen3-32b:free",name:"Qwen3 32B (free)",match:{equals:"qwen3-32b:free"},prices:{}},{id:"qwen3-8b",name:"Qwen3 8B",match:{equals:"qwen3-8b"},prices:{input_mtok:.035,output_mtok:.138}},{id:"qwen3-8b:free",name:"Qwen3 8B (free)",match:{equals:"qwen3-8b:free"},prices:{}},{id:"qwen3.5-plus-02-15",name:"Qwen3.5 plus-02-15",match:{equals:"qwen3.5-plus-02-15"},prices:{input_mtok:.4,output_mtok:2.4}},{id:"qwerky-72b:free",name:"Qwerky 72B (free)",match:{equals:"qwerky-72b:free"},prices:{}},{id:"qwq-32b",name:"QwQ 32B",match:{equals:"qwq-32b"},prices:{input_mtok:.15,output_mtok:.2}},{id:"qwq-32b-arliai-rpr-v1:free",name:"QwQ 32B RpR v1 (free)",match:{equals:"qwq-32b-arliai-rpr-v1:free"},prices:{}},{id:"qwq-32b-preview",name:"QwQ 32B Preview",match:{equals:"qwq-32b-preview"},prices:{input_mtok:.2,output_mtok:.2}},{id:"qwq-32b:free",name:"QwQ 32B (free)",match:{equals:"qwq-32b:free"},prices:{}},{id:"r1-1776",name:"R1 1776",match:{equals:"r1-1776"},prices:{input_mtok:2,output_mtok:8}},{id:"raifle/sorcererlm-8x22b",match:{equals:"raifle/sorcererlm-8x22b"},prices:{input_mtok:4.5,output_mtok:4.5}},{id:"reka-flash-3:free",name:"Flash 3 (free)",match:{equals:"reka-flash-3:free"},prices:{}},{id:"rekaai/reka-flash-3:free",match:{equals:"rekaai/reka-flash-3:free"},prices:{}},{id:"remm-slerp-l2-13b",name:"ReMM SLERP 13B",match:{equals:"remm-slerp-l2-13b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"rocinante-12b",name:"Rocinante 12B",match:{equals:"rocinante-12b"},prices:{input_mtok:.25,output_mtok:.5}},{id:"sao10k/fimbulvetr-11b-v2",match:{equals:"sao10k/fimbulvetr-11b-v2"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"sao10k/l3-euryale-70b",match:{equals:"sao10k/l3-euryale-70b"},prices:{input_mtok:1.48,output_mtok:1.48}},{id:"sao10k/l3-lunaris-8b",match:{equals:"sao10k/l3-lunaris-8b"},prices:{input_mtok:.02,output_mtok:.05}},{id:"sao10k/l3.1-euryale-70b",match:{equals:"sao10k/l3.1-euryale-70b"},prices:{input_mtok:.7,output_mtok:.8}},{id:"sao10k/l3.3-euryale-70b",match:{equals:"sao10k/l3.3-euryale-70b"},prices:{input_mtok:.7,output_mtok:.8}},{id:"sarvam-m:free",name:"Sarvam-M (free)",match:{equals:"sarvam-m:free"},prices:{}},{id:"scb10x/llama3.1-typhoon2-70b-instruct",match:{equals:"scb10x/llama3.1-typhoon2-70b-instruct"},prices:{input_mtok:.88,output_mtok:.88}},{id:"scb10x/llama3.1-typhoon2-8b-instruct",match:{equals:"scb10x/llama3.1-typhoon2-8b-instruct"},prices:{input_mtok:.18,output_mtok:.18}},{id:"shisa-ai/shisa-v2-llama3.3-70b:free",match:{equals:"shisa-ai/shisa-v2-llama3.3-70b:free"},prices:{}},{id:"shisa-v2-llama3.3-70b:free",name:"Shisa V2 Llama 3.3 70B (free)",match:{equals:"shisa-v2-llama3.3-70b:free"},prices:{}},{id:"skyfall-36b-v2",name:"Skyfall 36B V2",match:{equals:"skyfall-36b-v2"},prices:{input_mtok:.5,output_mtok:.8}},{id:"sonar",name:"Sonar",match:{equals:"sonar"},prices:{input_mtok:1,output_mtok:1}},{id:"sonar-deep-research",name:"Sonar Deep Research",match:{equals:"sonar-deep-research"},prices:{input_mtok:2,output_mtok:8}},{id:"sonar-pro",name:"Sonar Pro",match:{equals:"sonar-pro"},prices:{input_mtok:3,output_mtok:15}},{id:"sonar-reasoning",name:"Sonar Reasoning",match:{equals:"sonar-reasoning"},prices:{input_mtok:1,output_mtok:5}},{id:"sonar-reasoning-pro",name:"Sonar Reasoning Pro",match:{equals:"sonar-reasoning-pro"},prices:{input_mtok:2,output_mtok:8}},{id:"sophosympatheia/midnight-rose-70b",match:{equals:"sophosympatheia/midnight-rose-70b"},prices:{input_mtok:.8,output_mtok:.8}},{id:"sophosympatheia/rogue-rose-103b-v0.2:free",match:{equals:"sophosympatheia/rogue-rose-103b-v0.2:free"},prices:{}},{id:"sorcererlm-8x22b",name:"SorcererLM 8x22B",match:{equals:"sorcererlm-8x22b"},prices:{input_mtok:4.5,output_mtok:4.5}},{id:"spotlight",name:"Spotlight",match:{equals:"spotlight"},prices:{input_mtok:.18,output_mtok:.18}},{id:"steelskull/l3.3-electra-r1-70b",match:{equals:"steelskull/l3.3-electra-r1-70b"},prices:{input_mtok:.7,output_mtok:.95}},{id:"thedrummer/anubis-pro-105b-v1",match:{equals:"thedrummer/anubis-pro-105b-v1"},prices:{input_mtok:.8,output_mtok:1}},{id:"thedrummer/rocinante-12b",match:{equals:"thedrummer/rocinante-12b"},prices:{input_mtok:.25,output_mtok:.5}},{id:"thedrummer/skyfall-36b-v2",match:{equals:"thedrummer/skyfall-36b-v2"},prices:{input_mtok:.5,output_mtok:.8}},{id:"thedrummer/unslopnemo-12b",match:{equals:"thedrummer/unslopnemo-12b"},prices:{input_mtok:.5,output_mtok:.5}},{id:"thudm/glm-4-32b:free",match:{equals:"thudm/glm-4-32b:free"},prices:{}},{id:"thudm/glm-z1-32b:free",match:{equals:"thudm/glm-z1-32b:free"},prices:{}},{id:"toppy-m-7b",name:"Toppy M 7B",match:{equals:"toppy-m-7b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"undi95/remm-slerp-l2-13b",match:{equals:"undi95/remm-slerp-l2-13b"},prices:{input_mtok:.5625,output_mtok:1.125}},{id:"undi95/toppy-m-7b",match:{equals:"undi95/toppy-m-7b"},prices:{input_mtok:.07,output_mtok:.07}},{id:"unslopnemo-12b",name:"UnslopNemo 12B",match:{equals:"unslopnemo-12b"},prices:{input_mtok:.45,output_mtok:.45}},{id:"valkyrie-49b-v1",name:"Valkyrie 49B V1",match:{equals:"valkyrie-49b-v1"},prices:{input_mtok:.5,output_mtok:.8}},{id:"virtuoso-large",name:"Virtuoso Large",match:{equals:"virtuoso-large"},prices:{input_mtok:.75,output_mtok:1.2}},{id:"virtuoso-medium-v2",name:"Virtuoso Medium V2",match:{equals:"virtuoso-medium-v2"},prices:{input_mtok:.5,output_mtok:.8}},{id:"weaver",name:"Weaver (alpha)",match:{equals:"weaver"},prices:{input_mtok:1.5,output_mtok:1.5}},{id:"wizardlm-2-8x22b",name:"WizardLM-2 8x22B",match:{equals:"wizardlm-2-8x22b"},prices:{input_mtok:.48,output_mtok:.48}},{id:"x-ai/grok-2-1212",match:{equals:"x-ai/grok-2-1212"},prices:{input_mtok:2,output_mtok:10}},{id:"x-ai/grok-2-vision-1212",match:{equals:"x-ai/grok-2-vision-1212"},prices:{input_mtok:2,output_mtok:10}},{id:"x-ai/grok-3-beta",match:{equals:"x-ai/grok-3-beta"},prices:{input_mtok:3,output_mtok:15}},{id:"x-ai/grok-3-mini-beta",match:{equals:"x-ai/grok-3-mini-beta"},prices:{input_mtok:.3,output_mtok:.5}},{id:"x-ai/grok-4-fast",match:{equals:"x-ai/grok-4-fast"},context_window:2e6,prices:{input_mtok:{base:.2,tiers:[{start:128e3,price:.4}]},cache_read_mtok:.05,output_mtok:{base:.5,tiers:[{start:128e3,price:1}]}}},{id:"x-ai/grok-4.1-fast:free",match:{equals:"x-ai/grok-4.1-fast:free"},context_window:2e6,prices:{}},{id:"x-ai/grok-beta",match:{equals:"x-ai/grok-beta"},prices:{input_mtok:5,output_mtok:15}},{id:"x-ai/grok-code-fast-1",match:{equals:"x-ai/grok-code-fast-1"},context_window:256e3,prices:{input_mtok:.2,cache_read_mtok:.02,output_mtok:1.5}},{id:"x-ai/grok-vision-beta",match:{equals:"x-ai/grok-vision-beta"},prices:{input_mtok:5,output_mtok:15}},{id:"xwin-lm/xwin-lm-70b",match:{equals:"xwin-lm/xwin-lm-70b"},prices:{input_mtok:3.75,output_mtok:3.75}},{id:"yi-large",name:"Yi Large",match:{equals:"yi-large"},prices:{input_mtok:3,output_mtok:3}},{id:"z-ai/glm-4.5",match:{equals:"z-ai/glm-4.5"},context_window:131072,prices:{input_mtok:.35,output_mtok:1.55}},{id:"z-ai/glm-4.6",match:{equals:"z-ai/glm-4.6"},context_window:202752,prices:{input_mtok:.4,output_mtok:1.75}}]},{id:"ovhcloud",name:"OVHcloud AI Endpoints",pricing_urls:["https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/models"],api_pattern:"https://oai\\.endpoints\\.kepler\\.ai\\.cloud\\.ovh\\.net",extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"DeepSeek-R1-Distill-Llama-70B",name:"DeepSeek-R1-Distill-Llama-70B",match:{or:[{equals:"DeepSeek-R1-Distill-Llama-70B"},{equals:"deepseek-r1-distill-llama-70b"}]},context_window:131072,prices:{input_mtok:.74,output_mtok:.74}},{id:"Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"Llama-3.1-8B-Instruct"},{equals:"llama-3.1-8b-instruct"}]},context_window:131072,prices:{input_mtok:.11,output_mtok:.11}},{id:"Meta-Llama-3_3-70B-Instruct",name:"Meta-Llama-3_3-70B-Instruct",match:{or:[{equals:"Meta-Llama-3_3-70B-Instruct"},{equals:"meta-llama-3_3-70b-instruct"}]},context_window:131072,prices:{input_mtok:.74,output_mtok:.74}},{id:"Mistral-7B-Instruct-v0.3",name:"Mistral-7B-Instruct-v0.3",match:{or:[{equals:"Mistral-7B-Instruct-v0.3"},{equals:"mistral-7b-instruct-v0.3"}]},context_window:65536,prices:{input_mtok:.11,output_mtok:.11}},{id:"Mistral-Nemo-Instruct-2407",name:"Mistral-Nemo-Instruct-2407",match:{or:[{equals:"Mistral-Nemo-Instruct-2407"},{equals:"mistral-nemo-instruct-2407"}]},context_window:65536,prices:{input_mtok:.14,output_mtok:.14}},{id:"Mistral-Small-3.2-24B-Instruct-2506",name:"Mistral-Small-3.2-24B-Instruct-2506",match:{or:[{equals:"Mistral-Small-3.2-24B-Instruct-2506"},{equals:"mistral-small-3.2-24b-instruct-2506"}]},context_window:131072,prices:{input_mtok:.1,output_mtok:.31}},{id:"Mixtral-8x7B-Instruct-v0.1",name:"Mixtral-8x7B-Instruct-v0.1",match:{or:[{equals:"Mixtral-8x7B-Instruct-v0.1"},{equals:"mixtral-8x7b-instruct-v0.1"}]},context_window:32768,prices:{input_mtok:.7,output_mtok:.7}},{id:"Qwen2.5-VL-72B-Instruct",name:"Qwen2.5-VL-72B-Instruct",match:{or:[{equals:"Qwen2.5-VL-72B-Instruct"},{equals:"qwen2.5-vl-72b-instruct"}]},context_window:32768,prices:{input_mtok:1.01,output_mtok:1.01}},{id:"Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"Qwen3-32B"},{equals:"qwen3-32b"}]},context_window:32768,prices:{input_mtok:.09,output_mtok:.25}},{id:"Qwen3-Coder-30B-A3B-Instruct",name:"Qwen3-Coder-30B-A3B-Instruct",match:{or:[{equals:"Qwen3-Coder-30B-A3B-Instruct"},{equals:"qwen3-coder-30b-a3b-instruct"}]},context_window:262144,prices:{input_mtok:.07,output_mtok:.26}},{id:"bge-base-en-v1.5",name:"bge-base-en-v1.5",match:{equals:"bge-base-en-v1.5"},context_window:512,prices:{input_mtok:.01}},{id:"bge-m3",name:"bge-m3",match:{equals:"bge-m3"},context_window:8192,prices:{input_mtok:.01}},{id:"bge-multilingual-gemma2",name:"bge-multilingual-gemma2",match:{equals:"bge-multilingual-gemma2"},context_window:8192,prices:{input_mtok:.01}},{id:"gpt-oss-120b",name:"gpt-oss-120b",match:{equals:"gpt-oss-120b"},context_window:131072,prices:{input_mtok:.09,output_mtok:.47}},{id:"gpt-oss-20b",name:"gpt-oss-20b",match:{equals:"gpt-oss-20b"},context_window:131072,prices:{input_mtok:.05,output_mtok:.18}}]},{id:"perplexity",name:"Perplexity",pricing_urls:["https://docs.perplexity.ai/guides/pricing"],api_pattern:"https://api\\.perplexity\\.ai",price_comments:"Prices per request vary based on usage, this is not represented here, instead we just take the highest price shown for `requests_kcount`.",models:[{id:"llama-3.1-sonar-large-128k-online",name:"Llama 3.1 Sonar 70B Online",description:"Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance.",match:{equals:"llama-3.1-sonar-large-128k-online"},prices:{input_mtok:1,output_mtok:1}},{id:"llama-3.1-sonar-small-128k-online",name:"Llama 3.1 Sonar 8B Online",description:"Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance.",match:{equals:"llama-3.1-sonar-small-128k-online"},prices:{input_mtok:.2,output_mtok:.2}},{id:"r1-1776",name:"R1 1776",description:"R1 1776 is a version of DeepSeek-R1 that has been post-trained to remove censorship constraints related to topics restricted by the Chinese government. The model retains its original reasoning capabilities while providing direct responses to a wider range of queries. R1 1776 is an offline chat model that does not use the perplexity search subsystem.",match:{equals:"r1-1776"},prices:{input_mtok:2,output_mtok:8}},{id:"sonar",name:"Sonar",description:"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features optimized for speed.",match:{equals:"sonar"},prices:{input_mtok:1,output_mtok:1,requests_kcount:12}},{id:"sonar-deep-research",name:"Sonar Deep Research",description:"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers information. This enables comprehensive report generation across domains like finance, technology, health, and current events.",match:{equals:"sonar-deep-research"},prices:{input_mtok:2,output_mtok:8}},{id:"sonar-pro",name:"Sonar Pro",description:"Note: Sonar Pro pricing includes Perplexity search pricing. See details here",match:{equals:"sonar-pro"},prices:{input_mtok:3,output_mtok:15,requests_kcount:14}},{id:"sonar-reasoning",name:"Sonar Reasoning",description:"Sonar Reasoning is a reasoning model provided by Perplexity based on DeepSeek R1.",match:{equals:"sonar-reasoning"},prices:{input_mtok:1,output_mtok:5,requests_kcount:12}},{id:"sonar-reasoning-pro",name:"Sonar Reasoning Pro",description:"Sonar Pro pricing includes Perplexity search pricing.",match:{equals:"sonar-reasoning-pro"},prices:{input_mtok:2,output_mtok:8,requests_kcount:14}}]},{id:"together",name:"Together AI",pricing_urls:["https://www.together.ai/pricing"],api_pattern:"https://api\\.together\\.xyz",provider_match:{or:[{equals:"together-ai"},{equals:"together_ai"}]},models:[{id:"Austism/chronos-hermes-13b",match:{equals:"Austism/chronos-hermes-13b"},prices:{input_mtok:.3,output_mtok:.3}},{id:"Gryphe/MythoMax-L2-13b",match:{equals:"Gryphe/MythoMax-L2-13b"},prices:{input_mtok:.3,output_mtok:.3}},{id:"Nexusflow/NexusRaven-V2-13B",match:{equals:"Nexusflow/NexusRaven-V2-13B"},prices:{input_mtok:.3,output_mtok:.3}},{id:"NousResearch/Nous-Capybara-7B-V1p9",match:{equals:"NousResearch/Nous-Capybara-7B-V1p9"},prices:{input_mtok:.2,output_mtok:.2}},{id:"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",match:{equals:"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO"},prices:{input_mtok:.9,output_mtok:.9}},{id:"NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT",match:{equals:"NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT"},prices:{input_mtok:.9,output_mtok:.9}},{id:"NousResearch/Nous-Hermes-2-Yi-34B",match:{equals:"NousResearch/Nous-Hermes-2-Yi-34B"},prices:{input_mtok:.8,output_mtok:.8}},{id:"NousResearch/Nous-Hermes-Llama2-13b",match:{equals:"NousResearch/Nous-Hermes-Llama2-13b"},prices:{input_mtok:.225,output_mtok:.225}},{id:"NousResearch/Nous-Hermes-llama-2-7b",match:{equals:"NousResearch/Nous-Hermes-llama-2-7b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"Open-Orca/Mistral-7B-OpenOrca",match:{equals:"Open-Orca/Mistral-7B-OpenOrca"},prices:{input_mtok:.2,output_mtok:.2}},{id:"Qwen/Qwen1.5-0.5B",match:{or:[{equals:"Qwen/Qwen1.5-0.5B"},{equals:"Qwen/Qwen1.5-0.5B-Chat"}]},prices:{input_mtok:.1,output_mtok:.1}},{id:"Qwen/Qwen1.5-1.8B",match:{or:[{equals:"Qwen/Qwen1.5-1.8B"},{equals:"Qwen/Qwen1.5-1.8B-Chat"}]},prices:{input_mtok:.1,output_mtok:.1}},{id:"Qwen/Qwen1.5-14B",match:{or:[{equals:"Qwen/Qwen1.5-14B"},{equals:"Qwen/Qwen1.5-14B-Chat"}]},prices:{input_mtok:.3,output_mtok:.3}},{id:"Qwen/Qwen1.5-4B",match:{or:[{equals:"Qwen/Qwen1.5-4B"},{equals:"Qwen/Qwen1.5-4B-Chat"}]},prices:{input_mtok:.1,output_mtok:.1}},{id:"Qwen/Qwen1.5-72B",match:{equals:"Qwen/Qwen1.5-72B"},prices:{input_mtok:.9,output_mtok:.9}},{id:"Qwen/Qwen1.5-7B",match:{or:[{equals:"Qwen/Qwen1.5-7B"},{equals:"Qwen/Qwen1.5-7B-Chat"}]},prices:{input_mtok:.2,output_mtok:.2}},{id:"Undi95/ReMM-SLERP-L2-13B",match:{equals:"Undi95/ReMM-SLERP-L2-13B"},prices:{input_mtok:.3,output_mtok:.3}},{id:"Undi95/Toppy-M-7B",match:{equals:"Undi95/Toppy-M-7B"},prices:{input_mtok:.2,output_mtok:.2}},{id:"WizardLM/WizardLM-13B-V1.2",match:{equals:"WizardLM/WizardLM-13B-V1.2"},prices:{input_mtok:.3,output_mtok:.3}},{id:"allenai/OLMo-7B",match:{or:[{equals:"allenai/OLMo-7B"},{equals:"allenai/OLMo-7B-Instruct"},{equals:"allenai/OLMo-7B-Twin-2T"}]},prices:{input_mtok:.2,output_mtok:.2}},{id:"codellama/CodeLlama-13b-Instruct-hf",match:{equals:"codellama/CodeLlama-13b-Instruct-hf"},prices:{input_mtok:.225,output_mtok:.225}},{id:"codellama/CodeLlama-34b-Instruct-hf",match:{equals:"codellama/CodeLlama-34b-Instruct-hf"},prices:{input_mtok:.776,output_mtok:.776}},{id:"codellama/CodeLlama-70b-Instruct-hf",match:{equals:"codellama/CodeLlama-70b-Instruct-hf"},prices:{input_mtok:.9,output_mtok:.9}},{id:"codellama/CodeLlama-7b-Instruct-hf",match:{equals:"codellama/CodeLlama-7b-Instruct-hf"},prices:{input_mtok:.2,output_mtok:.2}},{id:"deepseek-ai/deepseek-coder-33b-instruct",match:{equals:"deepseek-ai/deepseek-coder-33b-instruct"},prices:{input_mtok:.8,output_mtok:.8}},{id:"garage-bAInd/Platypus2-70B-instruct",match:{equals:"garage-bAInd/Platypus2-70B-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"google/gemma-2b",match:{or:[{equals:"google/gemma-2b"},{equals:"google/gemma-2b-it"}]},prices:{input_mtok:.1,output_mtok:.1}},{id:"google/gemma-7b",match:{or:[{equals:"google/gemma-7b"},{equals:"google/gemma-7b-it"}]},prices:{input_mtok:.2,output_mtok:.2}},{id:"lmsys/vicuna-13b-v1.5",match:{equals:"lmsys/vicuna-13b-v1.5"},prices:{input_mtok:.3,output_mtok:.3}},{id:"lmsys/vicuna-7b-v1.5",match:{equals:"lmsys/vicuna-7b-v1.5"},prices:{input_mtok:.2,output_mtok:.2}},{id:"meta-llama/Llama-2-13b-chat-hf",match:{equals:"meta-llama/Llama-2-13b-chat-hf"},prices:{input_mtok:.225,output_mtok:.225}},{id:"meta-llama/Llama-2-70b-chat-hf",match:{equals:"meta-llama/Llama-2-70b-chat-hf"},prices:{input_mtok:.9,output_mtok:.9}},{id:"meta-llama/Llama-2-7b-chat-hf",match:{equals:"meta-llama/Llama-2-7b-chat-hf"},prices:{input_mtok:.2,output_mtok:.2}},{id:"meta-llama/Llama-3-70b-chat-hf",match:{equals:"meta-llama/Llama-3-70b-chat-hf"},prices:{input_mtok:.9,output_mtok:.9}},{id:"meta-llama/Llama-3-8b-chat-hf",match:{equals:"meta-llama/Llama-3-8b-chat-hf"},prices:{input_mtok:.2,output_mtok:.2}},{id:"meta-llama/Llama-3.3-70B-Instruct-Turbo",match:{equals:"meta-llama/Llama-3.3-70B-Instruct-Turbo"},prices:{input_mtok:.88,output_mtok:.88}},{id:"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",match:{equals:"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"},prices:{input_mtok:.27,output_mtok:.85}},{id:"meta-llama/Llama-4-Scout-17B-16E-Instruct",match:{equals:"meta-llama/Llama-4-Scout-17B-16E-Instruct"},prices:{input_mtok:.18,output_mtok:.59}},{id:"meta-llama/Meta-Llama-3-70B-Instruct-Lite",match:{equals:"meta-llama/Meta-Llama-3-70B-Instruct-Lite"},prices:{input_mtok:.54,output_mtok:.54}},{id:"meta-llama/Meta-Llama-3-70B-Instruct-Turbo",match:{equals:"meta-llama/Meta-Llama-3-70B-Instruct-Turbo"},prices:{input_mtok:.88,output_mtok:.88}},{id:"meta-llama/Meta-Llama-3-8B-Instruct-Lite",match:{equals:"meta-llama/Meta-Llama-3-8B-Instruct-Lite"},prices:{input_mtok:.1,output_mtok:.1}},{id:"meta-llama/Meta-Llama-3-8B-Instruct-Turbo",match:{equals:"meta-llama/Meta-Llama-3-8B-Instruct-Turbo"},prices:{input_mtok:.18,output_mtok:.18}},{id:"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",match:{equals:"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo"},prices:{input_mtok:3.5,output_mtok:3.5}},{id:"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",match:{equals:"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo"},prices:{input_mtok:.88,output_mtok:.88}},{id:"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",match:{equals:"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo"},prices:{input_mtok:.18,output_mtok:.18}},{id:"meta-llama/Meta-Llama-3.3-70B-Instruct-Turbo",match:{equals:"meta-llama/Meta-Llama-3.3-70B-Instruct-Turbo"},prices:{input_mtok:.88,output_mtok:.88}},{id:"microsoft/WizardLM-2-8x22B",match:{equals:"microsoft/WizardLM-2-8x22B"},prices:{input_mtok:1.2,output_mtok:1.2}},{id:"microsoft/phi-2",match:{equals:"microsoft/phi-2"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistralai/Mistral-7B-Instruct-v0.1",match:{equals:"mistralai/Mistral-7B-Instruct-v0.1"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistralai/Mistral-7B-Instruct-v0.2",match:{equals:"mistralai/Mistral-7B-Instruct-v0.2"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistralai/Mistral-7B-v0.1",match:{equals:"mistralai/Mistral-7B-v0.1"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistralai/Mixtral-8x22B-Instruct-v0.1",match:{equals:"mistralai/Mixtral-8x22B-Instruct-v0.1"},prices:{input_mtok:2.4,output_mtok:2.4}},{id:"mistralai/Mixtral-8x7B-Instruct-v0.1",match:{equals:"mistralai/Mixtral-8x7B-Instruct-v0.1"},prices:{input_mtok:.9,output_mtok:.9}},{id:"mistralai/Mixtral-8x7B-v0.1",match:{equals:"mistralai/Mixtral-8x7B-v0.1"},prices:{input_mtok:.9,output_mtok:.9}},{id:"openchat/openchat-3.5-1210",match:{equals:"openchat/openchat-3.5-1210"},prices:{input_mtok:.2,output_mtok:.2}},{id:"snorkelai/Snorkel-Mistral-PairRM-DPO",match:{equals:"snorkelai/Snorkel-Mistral-PairRM-DPO"},prices:{input_mtok:.2,output_mtok:.2}},{id:"teknium/OpenHermes-2-Mistral-7B",match:{equals:"teknium/OpenHermes-2-Mistral-7B"},prices:{input_mtok:.2,output_mtok:.2}},{id:"teknium/OpenHermes-2p5-Mistral-7B",match:{equals:"teknium/OpenHermes-2p5-Mistral-7B"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/GPT-JT-Moderation-6B",match:{equals:"togethercomputer/GPT-JT-Moderation-6B"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/Llama-2-7B-32K-Instruct",match:{equals:"togethercomputer/Llama-2-7B-32K-Instruct"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/RedPajama-INCITE-7B-Base",match:{equals:"togethercomputer/RedPajama-INCITE-7B-Base"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/RedPajama-INCITE-7B-Chat",match:{equals:"togethercomputer/RedPajama-INCITE-7B-Chat"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/RedPajama-INCITE-7B-Instruct",match:{equals:"togethercomputer/RedPajama-INCITE-7B-Instruct"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/RedPajama-INCITE-Base-3B-v1",match:{equals:"togethercomputer/RedPajama-INCITE-Base-3B-v1"},prices:{input_mtok:.1,output_mtok:.1}},{id:"togethercomputer/RedPajama-INCITE-Chat-3B-v1",match:{equals:"togethercomputer/RedPajama-INCITE-Chat-3B-v1"},prices:{input_mtok:.1,output_mtok:.1}},{id:"togethercomputer/RedPajama-INCITE-Instruct-3B-v1",match:{equals:"togethercomputer/RedPajama-INCITE-Instruct-3B-v1"},prices:{input_mtok:.1,output_mtok:.1}},{id:"togethercomputer/StripedHyena-Hessian-7B",match:{equals:"togethercomputer/StripedHyena-Hessian-7B"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/StripedHyena-Nous-7B",match:{equals:"togethercomputer/StripedHyena-Nous-7B"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/alpaca-7b",match:{equals:"togethercomputer/alpaca-7b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"upstage/SOLAR-10.7B-Instruct-v1.0",match:{equals:"upstage/SOLAR-10.7B-Instruct-v1.0"},prices:{input_mtok:.3,output_mtok:.3}},{id:"zero-one-ai/Yi-34B",match:{equals:"zero-one-ai/Yi-34B"},prices:{input_mtok:.8,output_mtok:.8}},{id:"zero-one-ai/Yi-6B",match:{equals:"zero-one-ai/Yi-6B"},prices:{input_mtok:.2,output_mtok:.2}}]},{id:"x-ai",name:"X AI",pricing_urls:["https://docs.x.ai/docs/models"],api_pattern:"https://api\\.x\\.ai",model_match:{contains:"grok"},provider_match:{equals:"xai"},extractors:[{api_flavor:"default",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:"cached_prompt_text_tokens",dest:"cache_read_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"grok-2-1212",name:"Grok 2 1212",description:"(deprecated) Grok 2 1212 introduces significant enhancements to accuracy, instruction adherence, and multilingual support, making it a powerful and flexible choice for developers seeking a highly steerable, intelligent model.",match:{or:[{equals:"grok-2-1212"},{equals:"grok-2"},{equals:"grok-2-latest"}]},context_window:32768,prices:{input_mtok:2,output_mtok:10},deprecated:!0},{id:"grok-2-vision-1212",name:"Grok 2 Vision 1212",description:"Our multimodal model that processes documents, diagrams, charts, screenshots, and photographs.",match:{or:[{equals:"grok-2-vision-1212"},{equals:"grok-2-vision"},{equals:"grok-2-vision-latest"}]},context_window:32768,prices:{input_mtok:2,output_mtok:10}},{id:"grok-3",name:"Grok 3",description:"Flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science.",match:{or:[{equals:"grok-3"},{equals:"grok-3-latest"},{equals:"grok-3-beta"}]},context_window:131072,prices:{input_mtok:3,cache_read_mtok:.75,output_mtok:15}},{id:"grok-3-fast",name:"Grok 3 Fast",description:"Excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science.",match:{or:[{equals:"grok-3-fast"},{equals:"grok-3-fast-latest"},{equals:"grok-3-fast-beta"}]},context_window:131072,prices:{input_mtok:5,cache_read_mtok:1.25,output_mtok:25}},{id:"grok-3-mini",name:"Grok 3 Mini",description:"A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.",match:{or:[{equals:"grok-3-mini"},{equals:"grok-3-mini-beta"},{equals:"grok-3-mini-latest"}]},context_window:131072,prices:{input_mtok:.3,cache_read_mtok:.075,output_mtok:.5}},{id:"grok-3-mini-fast",name:"Grok 3 Mini Fast",description:"A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.",match:{or:[{equals:"grok-3-mini-fast"},{equals:"grok-3-mini-fast-beta"},{equals:"grok-3-mini-fast-latest"}]},context_window:131072,prices:{input_mtok:.6,cache_read_mtok:.15,output_mtok:4}},{id:"grok-4-0709",name:"Grok 4",description:"A flagship model, offering unparalleled performance in natural language, math and reasoning - the perfect jack of all trades.",match:{or:[{equals:"grok-4-0709"},{equals:"grok-4"},{equals:"grok-4-latest"}]},context_window:256e3,prices:{input_mtok:3,cache_read_mtok:.75,output_mtok:15}},{id:"grok-4-1-fast-non-reasoning",name:"Grok 4.1 Fast Non-Reasoning",description:"A frontier multimodal model optimized specifically for high-performance agentic tool calling.",match:{or:[{equals:"grok-4-1-fast-non-reasoning"},{equals:"grok-4-1-fast-non-reasoning-latest"}]},context_window:2e6,prices:{input_mtok:.2,cache_read_mtok:.05,output_mtok:.5}},{id:"grok-4-1-fast-reasoning",name:"Grok 4.1 Fast Reasoning",description:"A frontier multimodal model optimized specifically for high-performance agentic tool calling.",match:{or:[{equals:"grok-4-1-fast"},{equals:"grok-4-1-fast-reasoning"},{equals:"grok-4-1-fast-reasoning-latest"}]},context_window:2e6,prices:{input_mtok:.2,cache_read_mtok:.05,output_mtok:.5}},{id:"grok-4-fast-non-reasoning",name:"Grok 4 Fast Non-Reasoning",description:"A frontier multimodal model optimized specifically for high-performance agentic tool calling.",match:{or:[{equals:"grok-4-fast-non-reasoning"},{equals:"grok-4-fast-non-reasoning-latest"}]},context_window:2e6,prices:{input_mtok:.2,cache_read_mtok:.05,output_mtok:.5}},{id:"grok-4-fast-reasoning",name:"Grok 4 Fast Reasoning",description:"A frontier multimodal model optimized specifically for high-performance agentic tool calling.",match:{or:[{equals:"grok-4-fast"},{equals:"grok-4-fast-reasoning"},{equals:"grok-4-fast-reasoning-latest"}]},context_window:2e6,prices:{input_mtok:.2,cache_read_mtok:.05,output_mtok:.5}},{id:"grok-4.3",name:"Grok 4.3",description:"Most advanced flagship model, leading the industry in non-hallucination rate, agentic tool calling, and instruction following capabilities. Supports text and image inputs with text outputs, function calling, structured outputs, and reasoning.",match:{or:[{equals:"grok-4.3"},{equals:"grok-4.3-latest"},{equals:"grok-latest"}]},context_window:1e6,prices:{input_mtok:1.25,cache_read_mtok:.2,output_mtok:2.5}},{id:"grok-code-fast-1",name:"Grok Code Fast 1",description:"A speedy and economical reasoning model that excels at agentic coding.",match:{or:[{equals:"grok-code-fast"},{equals:"grok-code-fast-1"},{equals:"grok-code-fast-1-0825"}]},context_window:256e3,prices:{input_mtok:.2,cache_read_mtok:.02,output_mtok:1.5}}]},{id:"zhipuai",name:"Zhipu AI",pricing_urls:["https://open.bigmodel.cn/pricing","https://docs.bigmodel.cn/cn/guide/start/model-overview"],api_pattern:"https://open\\.bigmodel\\.cn",price_comments:"Prices sourced from Zhipu AI open platform pricing (CNY, open.bigmodel.cn/pricing), converted to USD at 1 USD = 7.25 CNY (May 2026). Zhipu AI does not publish USD prices; CNY is the only billing currency. Flagship models (GLM-4.5-Air, GLM-4.7, GLM-5 series) have tiered pricing by input/output length; prices shown are for the cheapest tier ([0, 32k) input / [0, 0.2k) output where applicable). GLM-4 standard inference models (GLM-4-Air, GLM-4-Plus, etc.) bill input and output tokens at the same per-token rate per their pricing page. Cache write is temporarily free for flagship models (limited-time promotion, not included).",model_match:{or:[{starts_with:"GLM-"},{starts_with:"glm-"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"GLM-4-Air",name:"GLM-4-Air",description:"High-performance GLM-4 model with context caching. 128,000 token context window. Input and output billed at the same per-token rate.",match:{or:[{equals:"GLM-4-Air"},{equals:"glm-4-air"}]},context_window:128e3,prices:{input_mtok:.069,cache_read_mtok:.034,output_mtok:.069}},{id:"GLM-4-AirX",name:"GLM-4-AirX",description:"Fastest GLM-4 model. 8,000 token context window. Does not support context caching. Input and output billed at the same per-token rate.",match:{or:[{equals:"GLM-4-AirX"},{equals:"glm-4-airx"}]},context_window:8e3,prices:{input_mtok:1.379,output_mtok:1.379}},{id:"GLM-4-Assistant",name:"GLM-4-Assistant",description:"GLM-4 agent/assistant model. 128,000 token context window. Does not support context caching. Input and output billed at the same per-token rate.",match:{or:[{equals:"GLM-4-Assistant"},{equals:"glm-4-assistant"}]},context_window:128e3,prices:{input_mtok:.69,output_mtok:.69}},{id:"GLM-4-FlashX-250414",name:"GLM-4-FlashX-250414",description:"Fast and cheap GLM-4 model with context caching. 128,000 token context window. Input and output billed at the same per-token rate.",match:{or:[{equals:"GLM-4-FlashX-250414"},{equals:"glm-4-flashx-250414"}]},context_window:128e3,prices:{input_mtok:.014,cache_read_mtok:.007,output_mtok:.014}},{id:"GLM-4-Long",name:"GLM-4-Long",description:"GLM-4 model optimized for long inputs with context caching. 1,000,000 token context window. Input and output billed at the same per-token rate.",match:{or:[{equals:"GLM-4-Long"},{equals:"glm-4-long"}]},context_window:1e6,prices:{input_mtok:.138,cache_read_mtok:.069,output_mtok:.138}},{id:"GLM-4-Plus",name:"GLM-4-Plus",description:"Flagship GLM-4 model with context caching. 128,000 token context window. Input and output billed at the same per-token rate.",match:{or:[{equals:"GLM-4-Plus"},{equals:"glm-4-plus"}]},context_window:128e3,prices:{input_mtok:.69,cache_read_mtok:.345,output_mtok:.69}},{id:"GLM-4.5-Air",name:"GLM-4.5-Air",description:"Zhipu AI's GLM-4.5-Air flagship model with context caching. 128,000 token context window. Tiered pricing; prices shown for [0, 32k) input / [0, 0.2k) output tier.",match:{or:[{equals:"GLM-4.5-Air"},{equals:"glm-4.5-air"}]},context_window:128e3,prices:{input_mtok:.11,cache_read_mtok:.022,output_mtok:.276}},{id:"GLM-4.7",name:"GLM-4.7",description:"Zhipu AI's GLM-4.7 flagship model with context caching. 200,000 token context window. Tiered pricing; prices shown for [0, 32k) input / [0, 0.2k) output tier.",match:{or:[{equals:"GLM-4.7"},{equals:"glm-4.7"}]},context_window:2e5,prices:{input_mtok:.276,cache_read_mtok:.055,output_mtok:1.103}},{id:"GLM-4.7-FlashX",name:"GLM-4.7-FlashX",description:"Fast and affordable GLM-4.7 model with context caching. 200,000 token context window.",match:{or:[{equals:"GLM-4.7-FlashX"},{equals:"glm-4.7-flashx"}]},context_window:2e5,prices:{input_mtok:.069,cache_read_mtok:.014,output_mtok:.414}},{id:"GLM-5",name:"GLM-5",description:"Zhipu AI GLM-5 model with context caching. 200,000 token context window. Tiered pricing; prices shown for [0, 32k) input tier.",match:{or:[{equals:"GLM-5"},{equals:"glm-5"}]},context_window:2e5,prices:{input_mtok:.552,cache_read_mtok:.138,output_mtok:2.483}},{id:"GLM-5-Turbo",name:"GLM-5-Turbo",description:"Zhipu AI GLM-5 Turbo model with context caching. 200,000 token context window. Tiered pricing; prices shown for [0, 32k) input tier.",match:{or:[{equals:"GLM-5-Turbo"},{equals:"glm-5-turbo"}]},context_window:2e5,prices:{input_mtok:.69,cache_read_mtok:.166,output_mtok:3.034}},{id:"GLM-5.1",name:"GLM-5.1",description:"Zhipu AI's latest flagship model supporting long-horizon tasks, structured output, function calling, and context caching. 200,000 token context window. Tiered pricing; prices shown for [0, 32k) input tier.",match:{or:[{equals:"GLM-5.1"},{equals:"glm-5.1"}]},context_window:2e5,prices:{input_mtok:.828,cache_read_mtok:.179,output_mtok:3.31}}]}];function T(t,e,i){if(e<=0)return 0;let a=t.base;for(const o of t.tiers)i>o.start&&(a=o.price);return a*e/1e6}function d(t,e,i,a){return t===void 0||e===void 0?0:typeof t=="number"?t*e/1e6:T(t,e,a)}function S(t,e){let i=0,a=0;const o=t.input_tokens??0,r=t.cache_read_tokens??0,m=t.cache_write_tokens??0,n=t.cache_audio_read_tokens??0,s=t.input_audio_tokens??0,c=t.output_audio_tokens??0,u=e.cache_audio_read_mtok===void 0?0:n,p=e.cache_audio_read_mtok===void 0&&e.cache_read_mtok!==void 0?n:0;let l=0;if(e.input_audio_mtok!==void 0&&(l=s-u-p),l<0)throw new Error("cache_audio_read_tokens cannot be greater than input_audio_tokens");let w=0;if(e.cache_read_mtok!==void 0&&(w=r-u),w<0)throw new Error("cache_audio_read_tokens cannot be greater than cache_read_tokens");const I=e.cache_write_mtok===void 0?0:m;let b=0;if(e.input_mtok!==void 0&&(b=o-w-I-l-u),b<0)throw new Error("Uncached text input tokens cannot be negative");i+=d(e.input_mtok,b,"input_mtok",o),i+=d(e.cache_read_mtok,w,"cache_read_mtok",o),i+=d(e.cache_write_mtok,I,"cache_write_mtok",o),i+=d(e.input_audio_mtok,l,"input_audio_mtok",o),i+=d(e.cache_audio_read_mtok,u,"cache_audio_read_mtok",o);let f=0;if(e.output_mtok!==void 0&&(f=(t.output_tokens??0)-(e.output_audio_mtok===void 0?0:c)),f<0)throw new Error("output_audio_tokens cannot be greater than output_tokens");a+=d(e.output_mtok,f,"output_mtok",o),a+=d(e.output_audio_mtok,t.output_audio_tokens,"output_audio_mtok",o);let L=i+a;return e.requests_kcount!==void 0&&(L+=e.requests_kcount/1e3),{input_price:i,output_price:a,total_price:L}}function z(t,e){if(!Array.isArray(t.prices))return t.prices;for(let i=t.prices.length-1;i>=0;i--){const a=t.prices[i],o=a.constraint;if(o===void 0)return a.prices;if(o.type==="start_date"){if(e>=new Date(o.start_date))return a.prices}else{const r=e.toISOString().slice(11,19),m=o.start_time,n=o.end_time;if(n<m){if(r>=m||r<n)return a.prices}else if(r>=m&&r<n)return a.prices}}return t.prices[0].prices}function g(t,e){return"or"in t?t.or.some(i=>g(i,e)):"and"in t?t.and.every(i=>g(i,e)):"equals"in t?e.toLowerCase()===t.equals.toLowerCase():"starts_with"in t?e.toLowerCase().startsWith(t.starts_with.toLowerCase()):"ends_with"in t?e.toLowerCase().endsWith(t.ends_with.toLowerCase()):"contains"in t?e.toLowerCase().includes(t.contains.toLowerCase()):"regex"in t?new RegExp(t.regex).test(e):!1}function C(t,e){const i=e.toLowerCase().trim(),a=t.find(o=>o.id===i);return a||t.find(o=>o.provider_match&&g(o.provider_match,i))}function x(t,{modelId:e,providerApiUrl:i,providerId:a}){if(a){const o=C(t,a);if(o||a.toLowerCase()!=="litellm")return o}if(i)return t.find(o=>new RegExp(o.api_pattern).test(i));if(e)return t.find(o=>o.model_match&&g(o.model_match,e))}function R(t,e){return t.find(i=>g(i.match,e))}function P(t,e,i){const a=R(t.models,e);if(a)return a;if(t.fallback_model_providers&&i)for(const o of t.fallback_model_providers){const r=i.find(m=>m.id===o);if(r){const m=P(r,e);if(m)return m}}}const G="https://raw.githubusercontent.com/pydantic/genai-prices/main/prices/data.json";let h=Q,B=Promise.resolve(Q),M=null;function D(t){t!==null&&("then"in t?(B=t,t.then(e=>{e!==null&&(h=e)})):(B=Promise.resolve(t),h=t))}function N(t){M=t}function V(t){t({onCalc:N,remoteDataUrl:G,setProviderData:D})}function F(){return B}function E(t,e,i){M?.();let a=e.toLowerCase().trim(),o=i?.providerId;if(o&&o.toLowerCase()==="litellm"&&a.includes("/")){const u=a.indexOf("/"),p=a.slice(0,u),l=a.slice(u+1);p&&l&&x(h,{providerId:p})&&(o=p,a=l)}const r=i?.provider??x(h,{modelId:a,providerApiUrl:i?.providerApiUrl,providerId:o});if(!r)return null;const m=P(r,a,h);if(!m)return null;const n=i?.timestamp??new Date,s=z(m,n),c=S(t,s);return{auto_update_timestamp:void 0,model:m,model_price:s,provider:r,...c}}function O(t){return M?.(),x(h,t)}function K(t,e,i){if(i=i??"default",!t.extractors)throw new Error("No extraction logic defined for this provider");const a=t.extractors.find(s=>s.api_flavor===i);if(!a){const s=t.extractors.map(c=>c.api_flavor).join(", ");throw new Error(`Unknown apiFlavor '${i}', allowed values: ${s}`)}if(!q.guard(e))throw new Error(`Expected response data to be a mapping object, got ${_(e)}`);const o=v(a.model_path,e,H,!1,[]),r=A(a.root),m=v(r,e,q,!0,[]),n={};for(const s of a.mappings){const c=v(s.path,m,U,s.required,r);if(c!==null){const u=n[s.dest]??0;n[s.dest]=u+c}}if(!Object.keys(n).length)throw new Error(`No usage information found at ${JSON.stringify(a.root)}`);return{model:o,usage:n}}function v(t,e,i,a,o){const[r,...m]=A(t).reverse();if(typeof r!="string")throw new Error(`Expected last step of path to be a string, got ${_(r)}`);m.reverse();let n=e;const s=[];for(const u of m){if(s.push(u),typeof u=="object")if(Array.isArray(n))n=j(u,n);else{if(a)throw new Error(`Expected \`${k(o,s)}\` value to be a mapping, got ${_(n)}`);return null}else if(q.guard(n))n=n[u];else{if(a)throw new Error(`Expected \`${k(o,s)}\` value to be a mapping, got ${_(n)}`);return null}if(typeof n>"u")if(a){const p=typeof u=="object"?"Unable to find item":"Missing value";throw new Error(`${p} at \`${k(o,s)}\``)}else return null}if(!q.guard(n)){if(a)throw new Error(`Expected \`${k(o,s)}\` value to be a mapping, got ${_(n)}`);return null}const c=n[r];if(typeof c>"u"){if(a)throw s.push(r),new Error(`Missing value at \`${k(o,s)}\``);return null}if(i.guard(c))return c;if(a)throw s.push(r),new Error(`Expected \`${k(o,s)}\` value to be a ${i.name}, got ${_(c)}`);return null}function j(t,e){for(const i of e)if(q.guard(i)){const a=i[t.field];if(typeof a=="string"&&g(t.match,a))return i}}function A(t){return Array.isArray(t)?[...t]:[t]}function _(t){return t===null?"null":Array.isArray(t)?"array":typeof t=="object"?"mapping":typeof t}const q={guard:t=>_(t)==="mapping",name:"mapping"},H={guard:t=>typeof t=="string",name:"string"},U={guard:t=>typeof t=="number",name:"number"},k=(t,e)=>[...t.map(y),...e.map(y)].join("."),y=t=>typeof t=="string"?t:JSON.stringify(t);class ${base;tiers;constructor(e){this.base=e.base,this.tiers=[...e.tiers].sort((i,a)=>i.start-a.start)}}exports.REMOTE_DATA_JSON_URL=G;exports.TieredPrices=$;exports.calcPrice=E;exports.extractUsage=K;exports.findProvider=O;exports.updatePrices=V;exports.waitForUpdate=F;
10
+ - fluency in English, French, Italian, German, and Spanish`,match:{equals:"mixtral-8x22b-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"mixtral-8x7b",name:"Mixtral 8x7B",match:{or:[{starts_with:"mixtral-8x7b"},{equals:"open-mixtral-8x7b"}]},prices:{input_mtok:.7,output_mtok:.7}},{id:"pixtral-12b",name:"Pixtral 12B",description:"The first multi-modal, text+image-to-text model from Mistral AI. Its weights were launched via torrent: https://x.com/mistralai/status/1833758285167722836.",match:{or:[{equals:"pixtral-12b"},{equals:"pixtral-12b-latest"}]},prices:{input_mtok:.15,output_mtok:.15}},{id:"pixtral-large",name:"Pixtral Large 2411",description:"Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of Mistral Large 2. The model is able to understand documents, charts and natural images.",match:{or:[{equals:"pixtral-large-latest"},{equals:"pixtral-large-2411"}]},prices:{input_mtok:2,output_mtok:6}},{id:"voxtral-small-24b-2507",name:"Voxtral Small 24B 2507",description:"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.",match:{equals:"voxtral-small-24b-2507"},prices:{input_mtok:.1,cache_read_mtok:.01,output_mtok:.3}}]},{id:"moonshotai",name:"MoonshotAi",pricing_urls:["https://platform.moonshot.ai/docs/pricing/chat#product-pricing"],api_pattern:"https://api\\.moonshot\\.",model_match:{or:[{starts_with:"kimi"},{starts_with:"moonshot"}]},provider_match:{contains:"moonshot"},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"kimi-k2",name:"Kimi K2 0711",description:"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass.",match:{equals:"kimi-k2"},prices:{input_mtok:.57,output_mtok:2.3}},{id:"kimi-k2-0711-preview",name:"Kimi K2 0711 Preview",description:"MoE foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters.",match:{equals:"kimi-k2-0711-preview"},context_window:131072,prices:{input_mtok:.6,cache_read_mtok:.15,output_mtok:2.5}},{id:"kimi-k2-0905-preview",name:"Kimi K2 0905 Preview",description:"Based on kimi-k2-0711-preview, with enhanced agentic coding abilities, improved frontend code quality and practicality, and better context understanding. MoE foundation model with 1 trillion total parameters and 32 billion activated parameters.",match:{equals:"kimi-k2-0905-preview"},context_window:262144,prices:{input_mtok:.6,cache_read_mtok:.15,output_mtok:2.5}},{id:"kimi-k2-thinking",name:"Kimi K2 Thinking",description:"A thinking model with general agentic and reasoning capabilities, specializing in deep reasoning tasks.",match:{equals:"kimi-k2-thinking"},context_window:262144,prices:{input_mtok:.6,cache_read_mtok:.15,output_mtok:2.5}},{id:"kimi-k2-thinking-turbo",name:"Kimi K2 Thinking Turbo",description:"High-speed version of kimi-k2-thinking, suitable for scenarios requiring both deep reasoning and extremely fast responses.",match:{equals:"kimi-k2-thinking-turbo"},context_window:262144,prices:{input_mtok:1.15,cache_read_mtok:.15,output_mtok:8}},{id:"kimi-k2-turbo-preview",name:"Kimi K2 Turbo Preview",description:"High-speed version of kimi-k2, always aligned with the latest kimi-k2. Same model parameters as kimi-k2, output speed up to 60 tokens/sec (max 100 tokens/sec).",match:{starts_with:"kimi-k2-turbo"},context_window:262144,prices:{input_mtok:1.15,cache_read_mtok:.15,output_mtok:8}},{id:"kimi-k2.5",name:"Kimi K2.5",description:"Kimi's most versatile model featuring a native multimodal architecture that supports both visual and text input, thinking and non-thinking modes, and dialogue and agent tasks. Supports automatic context caching, ToolCalls, JSON Mode, Partial Mode, and internet search.",match:{starts_with:"kimi-k2.5"},context_window:262144,prices:{input_mtok:.6,cache_read_mtok:.1,output_mtok:3}},{id:"kimi-k2.6",name:"Kimi K2.6",description:"Kimi's most capable model with enhanced long-context coding stability, improved instruction compliance and self-correction capabilities. Native multimodal architecture supporting text, image, and video input, thinking and non-thinking modes, and agent tasks. Supports automatic context caching, ToolCalls, JSON Mode, Partial Mode, and internet search.",match:{starts_with:"kimi-k2.6"},context_window:262144,prices:{input_mtok:.95,cache_read_mtok:.16,output_mtok:4}},{id:"kimi-k2.7-code",name:"Kimi K2.7 Code",description:"Kimi's most intelligent coding model, capable of completing programming tasks with higher success rates in long context. It features a native multimodal architecture that supports text, image, video input, thinking modes, dialogue, and agent tasks.",match:{equals:"kimi-k2.7-code"},context_window:262144,price_comments:"Ref: https://platform.kimi.ai/docs/pricing/chat-k27-code.md",prices:{input_mtok:.95,cache_read_mtok:.19,output_mtok:4}},{id:"moonshot-v1-128k",name:"Moonshot V1 128K",match:{or:[{equals:"moonshot-v1-128k"},{equals:"moonshot-v1-128k-vision-preview"}]},context_window:131072,prices:{input_mtok:2,output_mtok:5}},{id:"moonshot-v1-32k",name:"Moonshot V1 32K",match:{or:[{equals:"moonshot-v1-32k"},{equals:"moonshot-v1-32k-vision-preview"}]},context_window:32768,prices:{input_mtok:1,output_mtok:3}},{id:"moonshot-v1-8k",name:"Moonshot V1 8K",match:{or:[{equals:"moonshot-v1-8k"},{equals:"moonshot-v1-8k-vision-preview"}]},context_window:8192,prices:{input_mtok:.2,output_mtok:2}}]},{id:"novita",name:"Novita",pricing_urls:["https://novita.ai/pricing"],api_pattern:"https://api\\.novita\\.ai",models:[{id:"Sao10K/L3-8B-Stheno-v3.2",match:{equals:"Sao10K/L3-8B-Stheno-v3.2"},prices:{input_mtok:.05,output_mtok:.05}},{id:"cognitivecomputations/dolphin-mixtral-8x22b",match:{equals:"cognitivecomputations/dolphin-mixtral-8x22b"},prices:{input_mtok:.9,output_mtok:.9}},{id:"deepseek/deepseek-r1",match:{equals:"deepseek/deepseek-r1"},prices:{input_mtok:4,output_mtok:4}},{id:"deepseek/deepseek-r1-distill-llama-70b",match:{equals:"deepseek/deepseek-r1-distill-llama-70b"},prices:{input_mtok:.8,output_mtok:.8}},{id:"deepseek/deepseek-r1-distill-llama-8b",match:{equals:"deepseek/deepseek-r1-distill-llama-8b"},prices:{input_mtok:.04,output_mtok:.04}},{id:"deepseek/deepseek-r1-distill-qwen-14b",match:{equals:"deepseek/deepseek-r1-distill-qwen-14b"},prices:{input_mtok:.15,output_mtok:.15}},{id:"deepseek/deepseek-r1-distill-qwen-32b",match:{equals:"deepseek/deepseek-r1-distill-qwen-32b"},prices:{input_mtok:.3,output_mtok:.3}},{id:"deepseek/deepseek_v3",match:{equals:"deepseek/deepseek_v3"},prices:{input_mtok:.89,output_mtok:.89}},{id:"google/gemma-2-9b-it",match:{equals:"google/gemma-2-9b-it"},prices:{input_mtok:.08,output_mtok:.08}},{id:"gryphe/mythomax-l2-13b",match:{equals:"gryphe/mythomax-l2-13b"},prices:{input_mtok:.09,output_mtok:.09}},{id:"jondurbin/airoboros-l2-70b",match:{equals:"jondurbin/airoboros-l2-70b"},prices:{input_mtok:.5,output_mtok:.5}},{id:"meta-llama/llama-3-70b-instruct",match:{equals:"meta-llama/llama-3-70b-instruct"},prices:{input_mtok:.51,output_mtok:.74}},{id:"meta-llama/llama-3-8b-instruct",match:{equals:"meta-llama/llama-3-8b-instruct"},prices:{input_mtok:.04,output_mtok:.04}},{id:"meta-llama/llama-3.1-70b-instruct",match:{equals:"meta-llama/llama-3.1-70b-instruct"},prices:{input_mtok:.34,output_mtok:.39}},{id:"meta-llama/llama-3.1-8b-instruct",match:{or:[{equals:"meta-llama/llama-3.1-8b-instruct"},{equals:"meta-llama/llama-3.1-8b-instruct-max"}]},prices:{input_mtok:.05,output_mtok:.05}},{id:"meta-llama/llama-3.1-8b-instruct-bf16",match:{equals:"meta-llama/llama-3.1-8b-instruct-bf16"},prices:{input_mtok:.06,output_mtok:.06}},{id:"meta-llama/llama-3.2-11b-vision-instruct",match:{equals:"meta-llama/llama-3.2-11b-vision-instruct"},prices:{input_mtok:.06,output_mtok:.06}},{id:"meta-llama/llama-3.2-1b-instruct",match:{equals:"meta-llama/llama-3.2-1b-instruct"},prices:{input_mtok:.02,output_mtok:.02}},{id:"meta-llama/llama-3.2-3b-instruct",match:{equals:"meta-llama/llama-3.2-3b-instruct"},prices:{input_mtok:.03,output_mtok:.05}},{id:"meta-llama/llama-3.3-70b-instruct",match:{equals:"meta-llama/llama-3.3-70b-instruct"},prices:{input_mtok:.39,output_mtok:.39}},{id:"microsoft/wizardlm-2-8x22b",match:{equals:"microsoft/wizardlm-2-8x22b"},prices:{input_mtok:.62,output_mtok:.62}},{id:"mistralai/mistral-7b-instruct",match:{equals:"mistralai/mistral-7b-instruct"},prices:{input_mtok:.059,output_mtok:.059}},{id:"mistralai/mistral-nemo",match:{equals:"mistralai/mistral-nemo"},prices:{input_mtok:.17,output_mtok:.17}},{id:"nousresearch/hermes-2-pro-llama-3-8b",match:{equals:"nousresearch/hermes-2-pro-llama-3-8b"},prices:{input_mtok:.14,output_mtok:.14}},{id:"nousresearch/nous-hermes-llama2-13b",match:{equals:"nousresearch/nous-hermes-llama2-13b"},prices:{input_mtok:.17,output_mtok:.17}},{id:"openchat/openchat-7b",match:{equals:"openchat/openchat-7b"},prices:{input_mtok:.06,output_mtok:.06}},{id:"qwen/qwen-2-7b-instruct",match:{equals:"qwen/qwen-2-7b-instruct"},prices:{input_mtok:.054,output_mtok:.054}},{id:"qwen/qwen-2-vl-72b-instruct",match:{equals:"qwen/qwen-2-vl-72b-instruct"},prices:{input_mtok:.45,output_mtok:.45}},{id:"qwen/qwen-2.5-72b-instruct",match:{equals:"qwen/qwen-2.5-72b-instruct"},prices:{input_mtok:.38,output_mtok:.4}},{id:"sao10k/l3-70b-euryale-v2.1",match:{equals:"sao10k/l3-70b-euryale-v2.1"},prices:{input_mtok:1.48,output_mtok:1.48}},{id:"sao10k/l3-8b-lunaris",match:{equals:"sao10k/l3-8b-lunaris"},prices:{input_mtok:.05,output_mtok:.05}},{id:"sao10k/l31-70b-euryale-v2.2",match:{equals:"sao10k/l31-70b-euryale-v2.2"},prices:{input_mtok:1.48,output_mtok:1.48}},{id:"sophosympatheia/midnight-rose-70b",match:{equals:"sophosympatheia/midnight-rose-70b"},prices:{input_mtok:.8,output_mtok:.8}},{id:"teknium/openhermes-2.5-mistral-7b",match:{equals:"teknium/openhermes-2.5-mistral-7b"},prices:{input_mtok:.17,output_mtok:.17}}]},{id:"openai",name:"OpenAI",pricing_urls:["https://platform.openai.com/docs/pricing","https://openai.com/api/pricing/","https://platform.openai.com/docs/models","https://help.openai.com/en/articles/7127956-how-much-does-gpt-4-cost"],api_pattern:"https://api\\.openai\\.com",model_match:{or:[{starts_with:"gpt-"},{regex:"^o[134]"}]},provider_match:{contains:"openai"},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"responses",root:"usage",model_path:"model",mappings:[{path:"input_tokens",dest:"input_tokens",required:!0},{path:["input_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:"output_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"embeddings",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0}]}],models:[{id:"ada",match:{or:[{equals:"ada"},{equals:"text-ada-001"}]},prices:{input_mtok:.4,output_mtok:.4}},{id:"babbage",match:{equals:"babbage"},prices:{input_mtok:.5,output_mtok:.5}},{id:"chatgpt-4o-latest",name:"ChatGPT-4o",description:"OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of GPT-4o in that it has additional RLHF. It is intended for research and evaluation.",match:{equals:"chatgpt-4o-latest"},prices:{input_mtok:5,output_mtok:15}},{id:"codex-mini",name:"Codex Mini",description:"codex-mini-latest is a fine-tuned version of o4-mini specifically for use in Codex CLI. For direct use in the API, we recommend starting with gpt-4.1.",match:{or:[{equals:"codex-mini"},{equals:"codex-mini-latest"}]},prices:{input_mtok:1.5,cache_read_mtok:.375,output_mtok:6}},{id:"computer-use",name:"Computer use",match:{starts_with:"computer-use"},prices:{input_mtok:3,output_mtok:12}},{id:"curie",match:{or:[{equals:"curie"},{equals:"text-curie-001"}]},prices:{input_mtok:2,output_mtok:2}},{id:"davinci",match:{or:[{equals:"davinci"},{equals:"text-davinci-001"}]},prices:{input_mtok:20,output_mtok:20}},{id:"ft:gpt-3.5-turbo-",description:"GPT-3.5 Turbo fine tuned.",match:{starts_with:"ft:gpt-3.5-turbo"},prices:{input_mtok:3,output_mtok:6}},{id:"ft:gpt-4o",description:"GPT-4o fine tuned.",match:{starts_with:"ft:gpt-4o-2024-"},prices:{input_mtok:3.75,output_mtok:15}},{id:"ft:gpt-4o-mini",description:"GPT-4o Mini fine tuned.",match:{starts_with:"ft:gpt-4o-mini-2024-"},prices:{input_mtok:.3,output_mtok:1.2}},{id:"gpt-3.5-0301",match:{or:[{equals:"gpt-3.5-turbo-0301"},{equals:"gpt-3.5-0301"}]},prices:{input_mtok:1.5,output_mtok:2}},{id:"gpt-3.5-turbo",name:"gpt 3.5 turbo",description:"GPT-3.5 Turbo offers a balance between cost and performance.",match:{or:[{equals:"gpt-3.5-turbo"},{equals:"gpt-35-turbo"},{equals:"gpt-3.5-turbo-0125"}]},context_window:16385,prices:{input_mtok:.5,output_mtok:1.5}},{id:"gpt-3.5-turbo-0613",match:{equals:"gpt-3.5-turbo-0613"},context_window:16385,prices:{input_mtok:1.5,output_mtok:2}},{id:"gpt-3.5-turbo-1106",match:{equals:"gpt-3.5-turbo-1106"},context_window:16385,prices:{input_mtok:1,output_mtok:2}},{id:"gpt-3.5-turbo-16k",name:"GPT-3.5 Turbo 16k",description:"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.",match:{or:[{equals:"gpt-3.5-turbo-16k"},{equals:"gpt-3.5-turbo-16k-0613"},{equals:"gpt-35-turbo-16k-0613"},{equals:"gpt-35-turbo-16k"}]},context_window:16385,prices:{input_mtok:3,output_mtok:4}},{id:"gpt-3.5-turbo-instruct",name:"gpt 3.5 turbo instruct",description:"GPT-3.5 Turbo offers a balance between cost and performance.",match:{or:[{starts_with:"gpt-3.5-turbo-instruct"},{equals:"gpt-3.5-turbo-instruct-0914"}]},context_window:16385,prices:{input_mtok:1.5,output_mtok:2}},{id:"gpt-4",name:"gpt 4",description:"GPT-4 is the latest and most advanced model in the GPT series, demonstrating sophisticated capabilities in complex reasoning, theory of mind, and narrative understanding.",match:{or:[{equals:"gpt-4"},{equals:"gpt-4-0314"},{equals:"gpt-4-0613"},{starts_with:"ft:gpt-4-0"}]},context_window:8192,prices:{input_mtok:30,output_mtok:60}},{id:"gpt-4-32k",name:"gpt 4",description:"GPT-4 is the latest and most advanced model in the GPT series, demonstrating sophisticated capabilities in complex reasoning, theory of mind, and narrative understanding.",match:{or:[{equals:"gpt-4-32k"},{equals:"gpt-4-32k-0314"},{equals:"gpt-4-32k-0613"}]},context_window:32e3,price_comments:"see https://help.openai.com/en/articles/7127956-how-much-does-gpt-4-cost",prices:{input_mtok:60,output_mtok:120}},{id:"gpt-4-turbo",name:"gpt 4 turbo",description:"GPT-4 Turbo offers a balance between cost and performance.",match:{or:[{equals:"gpt-4-turbo"},{equals:"gpt-4-turbo-2024-04-09"},{equals:"gpt-4-turbo-0125-preview"},{equals:"gpt-4-0125-preview"},{equals:"gpt-4-1106-preview"},{equals:"gpt-4-turbo-preview"}]},context_window:128e3,prices:{input_mtok:10,output_mtok:30}},{id:"gpt-4-vision-preview",name:"gpt 4 vision",description:"GPT-4 Vision is a model that offers a balance between cost and performance.",match:{or:[{equals:"gpt-4-vision-preview"},{equals:"gpt-4-1106-vision-preview"}]},context_window:128e3,prices:{input_mtok:10,output_mtok:30}},{id:"gpt-4.1",name:"gpt 4.1",description:"GPT-4.1 is OpenAI's latest flagship model, offering major improvements in coding, instruction following, and long context understanding with up to 1 million tokens of context.",match:{or:[{equals:"gpt-4.1"},{equals:"gpt-4.1-2025-04-14"}]},context_window:1e6,prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}},{id:"gpt-4.1-mini",name:"gpt 4.1 mini",description:"GPT-4.1 Mini is a significant leap in small model performance, matching or exceeding GPT-4o in many benchmarks while reducing latency by nearly half and cost by 83%.",match:{or:[{equals:"gpt-4.1-mini"},{equals:"gpt-4.1-mini-2025-04-14"}]},context_window:1e6,prices:{input_mtok:.4,cache_read_mtok:.1,output_mtok:1.6}},{id:"gpt-4.1-nano",name:"gpt 4.1 nano",description:"GPT-4.1 Nano is OpenAI's fastest and cheapest model, delivering exceptional performance for its size with a 1 million token context window, ideal for classification and autocompletion tasks.",match:{or:[{equals:"gpt-4.1-nano"},{equals:"gpt-4.1-nano-2025-04-14"}]},context_window:1e6,prices:{input_mtok:.1,cache_read_mtok:.025,output_mtok:.4}},{id:"gpt-4.5-preview",name:"GPT-4.5 (Preview)",description:"GPT-4.5 (Preview) is a research preview of OpenAI's latest language model, designed to advance capabilities in reasoning, creativity, and multi-turn conversation. It builds on previous iterations with improvements in world knowledge, contextual coherence, and the ability to follow user intent more effectively.",match:{starts_with:"gpt-4.5-preview"},prices:{input_mtok:75,cache_read_mtok:37.5,output_mtok:150}},{id:"gpt-4o",name:"gpt 4o",description:"GPT-4 Optimized (GPT-4o) is designed for high performance in reasoning, creativity, and technical tasks while maintaining consistent output quality.",match:{or:[{equals:"gpt-4o"},{equals:"gpt-4o-2024-05-13"},{equals:"gpt-4o-2024-08-06"},{equals:"gpt-4o-2024-11-20"}]},context_window:128e3,prices:{input_mtok:2.5,cache_read_mtok:1.25,output_mtok:10}},{id:"gpt-4o-audio-preview",name:"gpt 4o audio preview",description:"Audio model for gpt-4o",match:{starts_with:"gpt-4o-audio-preview"},context_window:128e3,prices:{input_mtok:2.5,output_mtok:10,input_audio_mtok:2.5}},{id:"gpt-4o-mini",name:"gpt 4o mini",description:"GPT-4o Mini is a cost-optimized variant of GPT-4o, designed for high-efficiency processing while maintaining strong performance. It excels in rapid inference and resource-efficient operations, making it ideal for production deployments requiring a balance of cost and capability.",match:{or:[{equals:"gpt-4o-mini"},{equals:"gpt-4o-mini-2024-07-18"},{equals:"gpt-4o-mini-search-preview"},{equals:"gpt-4o-mini-search-preview-2025-03-11"}]},context_window:128e3,prices:{input_mtok:.15,cache_read_mtok:.075,output_mtok:.6}},{id:"gpt-4o-mini-2024-07-18.ft-",description:"GPT-4o Mini fine tuned.",match:{starts_with:"gpt-4o-mini-2024-07-18.ft-"},prices:{input_mtok:.3,output_mtok:1.2}},{id:"gpt-4o-mini-audio-preview",name:"gpt 4o mini audio preview",description:"Audio model for gpt-4o mini",match:{starts_with:"gpt-4o-mini-audio"},prices:{input_mtok:.15,output_mtok:.6,input_audio_mtok:.15}},{id:"gpt-4o-mini-realtime-preview",match:{starts_with:"gpt-4o-mini-realtime"},prices:{input_mtok:.6,cache_read_mtok:.3,output_mtok:2.4,input_audio_mtok:10,cache_audio_read_mtok:.3,output_audio_mtok:20}},{id:"gpt-4o-mini-transcribe",match:{equals:"gpt-4o-mini-transcribe"},prices:{input_mtok:1.25,output_mtok:5,input_audio_mtok:3}},{id:"gpt-4o-mini-tts",match:{equals:"gpt-4o-mini-tts"},prices:{input_mtok:.6,output_mtok:12,output_audio_mtok:12}},{id:"gpt-4o-realtime-preview",match:{starts_with:"gpt-4o-realtime"},prices:{input_mtok:5,cache_read_mtok:2.5,output_mtok:20,input_audio_mtok:40,cache_audio_read_mtok:2.5,output_audio_mtok:80}},{id:"gpt-4o-search-preview",name:"GPT-4o Search Preview",description:"GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.",match:{or:[{equals:"gpt-4o-search-preview"},{equals:"gpt-4o-search-preview-2025-03-11"}]},prices:{input_mtok:2.5,output_mtok:10}},{id:"gpt-4o-transcribe",match:{or:[{equals:"gpt-4o-transcribe"},{equals:"gpt-4o-transcribe-diarize"}]},prices:{input_mtok:2.5,output_mtok:10,input_audio_mtok:6}},{id:"gpt-4o:extended",name:"GPT-4o (extended)",description:`GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.`,match:{equals:"gpt-4o:extended"},prices:{input_mtok:6,output_mtok:18}},{id:"gpt-5",name:"GPT-5",description:"GPT-5 is OpenAI's flagship model for coding, reasoning, and agentic tasks across domains.",match:{or:[{equals:"gpt-5"},{equals:"gpt-5-2025-08-07"},{equals:"gpt-5-chat"},{equals:"gpt-5-chat-latest"},{equals:"gpt-5-codex"}]},context_window:4e5,prices:{input_mtok:1.25,cache_read_mtok:.125,output_mtok:10}},{id:"gpt-5-image",match:{equals:"gpt-5-image"},price_comments:"Seen on OpenRouter before OpenAI",prices:{input_mtok:10,cache_read_mtok:1.25,output_mtok:10}},{id:"gpt-5-image-mini",match:{equals:"gpt-5-image-mini"},price_comments:"Seen on OpenRouter before OpenAI",prices:{input_mtok:2.5,cache_read_mtok:.25,output_mtok:2}},{id:"gpt-5-mini",name:"GPT-5 mini",description:"GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.",match:{or:[{equals:"gpt-5-mini"},{equals:"gpt-5-mini-2025-08-07"}]},context_window:4e5,prices:{input_mtok:.25,cache_read_mtok:.025,output_mtok:2}},{id:"gpt-5-nano",name:"GPT-5 nano",description:"GPT-5 Nano is OpenAI's fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.",match:{or:[{equals:"gpt-5-nano"},{starts_with:"gpt-5-nano-"}]},context_window:4e5,prices:{input_mtok:.05,cache_read_mtok:.005,output_mtok:.4}},{id:"gpt-5-pro",match:{or:[{equals:"gpt-5-pro"},{equals:"gpt-5-pro-2025-10-06"}]},context_window:4e5,prices:{input_mtok:15,output_mtok:120}},{id:"gpt-5.1",name:"GPT-5.1",description:"The best model for coding and agentic tasks across industries",match:{or:[{equals:"gpt-5.1"},{equals:"gpt-5.1-2025-11-13"},{equals:"gpt-5.1-codex"},{equals:"gpt-5.1-codex-max"},{equals:"gpt-5.1-chat"},{equals:"gpt-5.1-chat-latest"},{equals:"gpt-5-1"},{equals:"gpt-5-1-2025-11-13"},{equals:"gpt-5-1-codex"},{equals:"gpt-5-1-codex-max"},{equals:"gpt-5-1-chat"},{equals:"gpt-5-1-chat-latest"}]},context_window:4e5,prices:{input_mtok:1.25,cache_read_mtok:.125,output_mtok:10}},{id:"gpt-5.1-codex-mini",name:"GPT-5.1 Codex Mini",match:{or:[{equals:"gpt-5.1-codex-mini"},{equals:"gpt-5.1-mini"},{equals:"gpt-5-1-codex-mini"},{equals:"gpt-5-1-mini"}]},context_window:4e5,prices:{input_mtok:.25,cache_read_mtok:.025,output_mtok:2}},{id:"gpt-5.2",name:"GPT-5.2",description:"The best model for coding and agentic tasks across industries",match:{or:[{equals:"gpt-5.2"},{equals:"gpt-5.2-2025-12-11"},{equals:"gpt-5-2"},{equals:"gpt-5-2-2025-12-11"},{equals:"gpt-5.2-chat"},{equals:"gpt-5.2-chat-latest"},{equals:"gpt-5-2-chat"},{equals:"gpt-5-2-chat-latest"},{equals:"gpt-5.2-codex"},{equals:"gpt-5-2-codex"}]},context_window:4e5,prices:{input_mtok:1.75,cache_read_mtok:.175,output_mtok:14}},{id:"gpt-5.2-pro",description:"Version of GPT-5.2 that produces smarter and more precise responses.",match:{or:[{equals:"gpt-5.2-pro"},{equals:"gpt-5.2-pro-2025-12-11"},{equals:"gpt-5-2-pro-2025-12-11"}]},context_window:4e5,prices:{input_mtok:21,output_mtok:168}},{id:"gpt-5.3",name:"GPT-5.3 Chat",description:"GPT-5.3 Instant model used in ChatGPT",match:{or:[{equals:"gpt-5.3"},{equals:"gpt-5-3"},{equals:"gpt-5.3-chat"},{equals:"gpt-5.3-chat-latest"},{equals:"gpt-5-3-chat"},{equals:"gpt-5-3-chat-latest"}]},context_window:128e3,prices:{input_mtok:1.75,cache_read_mtok:.175,output_mtok:14}},{id:"gpt-5.3-codex",name:"GPT-5.3-Codex",description:"The most capable agentic coding model",match:{or:[{equals:"gpt-5.3-codex"},{equals:"gpt-5-3-codex"}]},context_window:4e5,prices:{input_mtok:1.75,cache_read_mtok:.175,output_mtok:14}},{id:"gpt-5.4",name:"GPT-5.4",description:"OpenAI's most capable model with a 1.05M token context window.",match:{or:[{equals:"gpt-5.4"},{equals:"gpt-5.4-2026-03-05"},{equals:"gpt-5-4"},{equals:"gpt-5-4-2026-03-05"}]},context_window:105e4,prices:{input_mtok:{base:2.5,tiers:[{start:272e3,price:5}]},cache_read_mtok:{base:.25,tiers:[{start:272e3,price:.5}]},output_mtok:{base:15,tiers:[{start:272e3,price:22.5}]}}},{id:"gpt-5.4-image-2",name:"GPT-5.4 Image 2",description:"GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows across reasoning, coding, and image generation.",match:{equals:"gpt-5.4-image-2"},price_comments:"Imported from OpenRouter pricing; verify against OpenAI pricing when native API pricing is published.",prices:{input_mtok:8,cache_read_mtok:2,output_mtok:15}},{id:"gpt-5.4-mini",name:"GPT-5.4 mini",description:"Our strongest mini model yet for coding, computer use, and subagents.",match:{or:[{equals:"gpt-5.4-mini"},{equals:"gpt-5.4-mini-2026-03-17"},{equals:"gpt-5-4-mini"},{equals:"gpt-5-4-mini-2026-03-17"}]},context_window:4e5,prices:{input_mtok:.75,cache_read_mtok:.075,output_mtok:4.5}},{id:"gpt-5.4-nano",name:"GPT-5.4 nano",description:"Our cheapest GPT-5.4-class model for simple high-volume tasks.",match:{or:[{equals:"gpt-5.4-nano"},{equals:"gpt-5.4-nano-2026-03-17"},{equals:"gpt-5-4-nano"},{equals:"gpt-5-4-nano-2026-03-17"}]},context_window:4e5,prices:{input_mtok:.2,cache_read_mtok:.02,output_mtok:1.25}},{id:"gpt-5.4-pro",name:"GPT-5.4 Pro",description:"Version of GPT-5.4 that produces smarter and more precise responses.",match:{or:[{equals:"gpt-5.4-pro"},{equals:"gpt-5.4-pro-2026-03-05"},{equals:"gpt-5-4-pro"},{equals:"gpt-5-4-pro-2026-03-05"}]},context_window:105e4,prices:{input_mtok:{base:30,tiers:[{start:272e3,price:60}]},output_mtok:{base:180,tiers:[{start:272e3,price:270}]}}},{id:"gpt-5.5",name:"GPT-5.5",description:"The best model for coding and agentic tasks across industries",match:{or:[{equals:"gpt-5.5"},{equals:"gpt-5.5-2026-04-23"},{equals:"gpt-5.5-2026-04-24"},{equals:"gpt-5-5"},{equals:"gpt-5-5-2026-04-23"},{equals:"gpt-5-5-2026-04-24"},{equals:"gpt-5.5-chat"},{equals:"gpt-5.5-chat-latest"},{equals:"gpt-5-5-chat"},{equals:"gpt-5-5-chat-latest"},{equals:"gpt-5.5-codex"},{equals:"gpt-5-5-codex"}]},context_window:1e6,prices:{input_mtok:5,cache_read_mtok:.5,output_mtok:30}},{id:"gpt-5.5-pro",name:"GPT-5.5 Pro",description:"Version of GPT-5.5 that produces smarter and more precise responses.",match:{or:[{equals:"gpt-5.5-pro"},{equals:"gpt-5.5-pro-2026-04-23"},{equals:"gpt-5-5-pro"},{equals:"gpt-5-5-pro-2026-04-23"}]},context_window:1e6,prices:{input_mtok:30,output_mtok:180}},{id:"gpt-audio",name:"GPT Audio",description:"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural-sounding voices and maintains better voice consistency.",match:{equals:"gpt-audio"},price_comments:"Imported from OpenRouter pricing; verify against OpenAI pricing when native API pricing is published.",prices:{input_mtok:2.5,output_mtok:10}},{id:"gpt-audio-mini",name:"GPT Audio Mini",description:"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.",match:{equals:"gpt-audio-mini"},price_comments:"Imported from OpenRouter pricing; verify against OpenAI pricing when native API pricing is published.",prices:{input_mtok:.6,output_mtok:2.4}},{id:"gpt-chat-latest",name:"GPT Chat Latest",description:"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT.",match:{equals:"gpt-chat-latest"},price_comments:"Imported from OpenRouter pricing; verify against OpenAI pricing when native API pricing is published.",prices:{input_mtok:5,cache_read_mtok:.5,output_mtok:30}},{id:"gpt-oss-120b",name:"gpt-oss-120b",description:"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.",match:{equals:"gpt-oss-120b"},price_comments:"Imported from OpenRouter pricing; verify against OpenAI pricing when native API pricing is published.",prices:{input_mtok:.039,output_mtok:.18}},{id:"gpt-oss-20b",name:"gpt-oss-20b",description:"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass.",match:{equals:"gpt-oss-20b"},price_comments:"Imported from OpenRouter pricing; verify against OpenAI pricing when native API pricing is published.",prices:{input_mtok:.029,output_mtok:.14}},{id:"gpt-oss-safeguard-20b",name:"gpt-oss-safeguard-20b",description:"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks.",match:{equals:"gpt-oss-safeguard-20b"},price_comments:"Imported from OpenRouter pricing; verify against OpenAI pricing when native API pricing is published.",prices:{input_mtok:.075,cache_read_mtok:.037,output_mtok:.3}},{id:"gpt-realtime",match:{or:[{equals:"gpt-realtime"},{equals:"gpt-realtime-2025-08-28"}]},price_comments:"Missing image token prices which we don't support yet",prices:{input_mtok:4,cache_read_mtok:.4,output_mtok:16,input_audio_mtok:32,cache_audio_read_mtok:.4,output_audio_mtok:64}},{id:"gpt-realtime-mini",match:{equals:"gpt-realtime-mini"},price_comments:"Missing image token prices which we don't support yet",prices:{input_mtok:.6,cache_read_mtok:.06,output_mtok:2.4,input_audio_mtok:10,cache_audio_read_mtok:.3,output_audio_mtok:20}},{id:"moderation",description:"All OpenAI moderation models and endpoints are free of charge",match:{contains:"moderation"},prices:{}},{id:"o1",name:"o1",description:"O1 is a model that offers a balance between cost and performance.",match:{or:[{equals:"o1"},{equals:"o1-2024-12-17"},{equals:"o1-preview"},{equals:"o1-preview-2024-09-12"}]},context_window:128e3,prices:{input_mtok:15,cache_read_mtok:7.5,output_mtok:60}},{id:"o1-mini",name:"o1 mini",description:"O1 Mini is a model that offers a balance between cost and performance.",match:{or:[{equals:"o1-mini"},{equals:"o1-mini-2024-09-12"}]},context_window:128e3,prices:{input_mtok:1.1,cache_read_mtok:.55,output_mtok:4.4}},{id:"o1-pro",name:"o1-pro",description:"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.",match:{or:[{equals:"o1-pro"},{equals:"o1-pro-2025-03-19"}]},prices:{input_mtok:150,output_mtok:600}},{id:"o3",name:"o3",description:"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images. Note that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations",match:{or:[{equals:"o3"},{equals:"o3-2025-04-16"}]},prices:[{prices:{input_mtok:10,cache_read_mtok:.5,output_mtok:40}},{constraint:{start_date:"2025-06-10",type:"start_date"},prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}}]},{id:"o3-deep-research",match:{or:[{equals:"o3-deep-research"},{equals:"o3-deep-research-2025-06-26"}]},prices:{input_mtok:10,cache_read_mtok:2.5,output_mtok:40}},{id:"o3-mini",name:"o3 Mini",description:"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding.",match:{or:[{equals:"o3-mini"},{equals:"o3-mini-2025-01-31"},{equals:"o3-mini-high"}]},prices:{input_mtok:1.1,cache_read_mtok:.55,output_mtok:4.4}},{id:"o3-pro",name:"o3 Pro",description:"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.",match:{or:[{equals:"o3-pro"},{equals:"o3-pro-2025-06-10"}]},prices:{input_mtok:20,output_mtok:80}},{id:"o4-mini",name:"o4 Mini High",description:"OpenAI o4-mini-high is the same model as o4-mini with reasoning_effort set to high.",match:{or:[{equals:"o4-mini-2025-04-16"},{equals:"o4-mini-high"},{equals:"o4-mini"}]},prices:{input_mtok:1.1,cache_read_mtok:.275,output_mtok:4.4}},{id:"o4-mini-deep-research",match:{or:[{equals:"o4-mini-deep-research"},{equals:"o4-mini-deep-research-2025-06-26"}]},prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}},{id:"text-davinci-002",match:{equals:"text-davinci-002"},prices:{input_mtok:20,output_mtok:20}},{id:"text-davinci-003",match:{equals:"text-davinci-003"},prices:{input_mtok:20,output_mtok:20}},{id:"text-embedding-3-large",name:"text embedding 3",description:"Text Embedding 3 is a model that offers a balance between cost and performance.",match:{equals:"text-embedding-3-large"},context_window:8192,prices:{input_mtok:.13}},{id:"text-embedding-3-small",name:"text embedding 3",description:"Text Embedding 3 is a model that offers a balance between cost and performance.",match:{equals:"text-embedding-3-small"},context_window:8192,prices:{input_mtok:.02}},{id:"text-embedding-ada-002",name:"text embedding ada",description:"Text Embedding Ada is a model that offers a balance between cost and performance.",match:{or:[{equals:"text-embedding-ada"},{equals:"text-embedding-ada-002"},{equals:"text-embedding-ada-002-v2"}]},context_window:8192,prices:{input_mtok:.1}}]},{id:"openrouter",name:"OpenRouter",pricing_urls:["https://openrouter.ai/models"],api_pattern:"https://(api\\.)?openrouter\\.ai",extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","cache_write_tokens"],dest:"cache_write_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"01-ai/yi-large",match:{equals:"01-ai/yi-large"},prices:{input_mtok:3,output_mtok:3}},{id:"aetherwiing/mn-starcannon-12b",match:{equals:"aetherwiing/mn-starcannon-12b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"agentica-org/deepcoder-14b-preview:free",match:{equals:"agentica-org/deepcoder-14b-preview:free"},prices:{}},{id:"ai21/jamba-1-5-large",match:{equals:"ai21/jamba-1-5-large"},prices:{input_mtok:2,output_mtok:8}},{id:"ai21/jamba-1-5-mini",match:{equals:"ai21/jamba-1-5-mini"},prices:{input_mtok:.2,output_mtok:.4}},{id:"ai21/jamba-1.6-large",match:{equals:"ai21/jamba-1.6-large"},prices:{input_mtok:2,output_mtok:8}},{id:"ai21/jamba-1.6-mini",match:{equals:"ai21/jamba-1.6-mini"},prices:{input_mtok:.2,output_mtok:.4}},{id:"ai21/jamba-instruct",match:{equals:"ai21/jamba-instruct"},prices:{input_mtok:.5,output_mtok:.7}},{id:"ai21/jamba-large-1.7",name:"Jamba Large 1.7",match:{equals:"ai21/jamba-large-1.7"},prices:{input_mtok:2,output_mtok:8}},{id:"aion-labs/aion-1.0",name:"Aion-1.0",match:{equals:"aion-labs/aion-1.0"},prices:{input_mtok:4,output_mtok:8}},{id:"aion-labs/aion-1.0-mini",name:"Aion-1.0-Mini",match:{equals:"aion-labs/aion-1.0-mini"},prices:{input_mtok:.7,output_mtok:1.4}},{id:"aion-labs/aion-2.0",name:"Aion-2.0",match:{equals:"aion-labs/aion-2.0"},prices:{input_mtok:.8,cache_read_mtok:.2,output_mtok:1.6}},{id:"aion-labs/aion-rp-llama-3.1-8b",match:{equals:"aion-labs/aion-rp-llama-3.1-8b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"alfredpros/codellama-7b-instruct-solidity",match:{equals:"alfredpros/codellama-7b-instruct-solidity"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"all-hands/openhands-lm-32b-v0.1",match:{equals:"all-hands/openhands-lm-32b-v0.1"},prices:{input_mtok:2.6,output_mtok:3.4}},{id:"allenai/molmo-7b-d:free",match:{equals:"allenai/molmo-7b-d:free"},prices:{}},{id:"allenai/olmo-3-32b-think",name:"Olmo 3 32B Think",match:{equals:"allenai/olmo-3-32b-think"},prices:{input_mtok:.15,output_mtok:.5}},{id:"alpindale/goliath-120b",match:{equals:"alpindale/goliath-120b"},prices:{input_mtok:6.5625,output_mtok:9.375}},{id:"alpindale/magnum-72b",match:{equals:"alpindale/magnum-72b"},prices:{input_mtok:1.5,output_mtok:2.25}},{id:"amazon/nova-2-lite-v1",name:"Nova 2 Lite",match:{equals:"amazon/nova-2-lite-v1"},prices:{input_mtok:.3,output_mtok:2.5}},{id:"amazon/nova-lite-v1",match:{equals:"amazon/nova-lite-v1"},prices:{input_mtok:.06,output_mtok:.24}},{id:"amazon/nova-micro-v1",match:{equals:"amazon/nova-micro-v1"},prices:{input_mtok:.035,output_mtok:.14}},{id:"amazon/nova-premier-v1",name:"Nova Premier 1.0",match:{equals:"amazon/nova-premier-v1"},prices:{input_mtok:2.5,cache_read_mtok:.625,output_mtok:12.5}},{id:"amazon/nova-pro-v1",match:{equals:"amazon/nova-pro-v1"},prices:{input_mtok:.8,output_mtok:3.2}},{id:"anthracite-org/magnum-v2-72b",match:{equals:"anthracite-org/magnum-v2-72b"},prices:{input_mtok:3,output_mtok:3}},{id:"anthracite-org/magnum-v4-72b",match:{equals:"anthracite-org/magnum-v4-72b"},prices:{input_mtok:1.5,output_mtok:2.25}},{id:"anthropic/claude-2",match:{or:[{equals:"anthropic/claude-2"},{equals:"anthropic/claude-2.0"},{equals:"anthropic/claude-2.0:beta"},{equals:"anthropic/claude-2.1"},{equals:"anthropic/claude-2.1:beta"},{equals:"anthropic/claude-2:beta"}]},prices:{input_mtok:8,output_mtok:24}},{id:"anthropic/claude-3-haiku",match:{or:[{equals:"anthropic/claude-3-haiku"},{equals:"anthropic/claude-3-haiku:beta"}]},prices:{input_mtok:.25,output_mtok:1.25}},{id:"anthropic/claude-3-opus",match:{or:[{equals:"anthropic/claude-3-opus"},{equals:"anthropic/claude-3-opus:beta"}]},prices:{input_mtok:15,output_mtok:75}},{id:"anthropic/claude-3-sonnet",match:{or:[{equals:"anthropic/claude-3-sonnet"},{equals:"anthropic/claude-3-sonnet:beta"}]},prices:{input_mtok:3,output_mtok:15}},{id:"anthropic/claude-3.5-haiku",match:{or:[{equals:"anthropic/claude-3.5-haiku"},{equals:"anthropic/claude-3.5-haiku-20241022"},{equals:"anthropic/claude-3.5-haiku-20241022:beta"},{equals:"anthropic/claude-3.5-haiku:beta"}]},prices:{input_mtok:.8,output_mtok:4}},{id:"anthropic/claude-3.5-sonnet",match:{or:[{equals:"anthropic/claude-3.5-sonnet"},{equals:"anthropic/claude-3.5-sonnet-20240620"},{equals:"anthropic/claude-3.5-sonnet-20240620:beta"},{equals:"anthropic/claude-3.5-sonnet:beta"}]},prices:{input_mtok:3,output_mtok:15}},{id:"anthropic/claude-3.7-sonnet",match:{or:[{equals:"anthropic/claude-3.7-sonnet"},{equals:"anthropic/claude-3.7-sonnet:beta"},{equals:"anthropic/claude-3.7-sonnet:thinking"}]},prices:{input_mtok:3,output_mtok:15}},{id:"anthropic/claude-fable-5",match:{or:[{equals:"anthropic/claude-fable-5"},{equals:"anthropic/claude-fable-5:beta"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:10,cache_write_mtok:12.5,cache_read_mtok:1,output_mtok:50}},{id:"anthropic/claude-haiku-4.5",match:{or:[{equals:"anthropic/claude-haiku-4.5"},{equals:"anthropic/claude-4.5-haiku-20251001"},{equals:"anthropic/claude-4.5-haiku-20251001:beta"},{equals:"anthropic/claude-haiku-4.5-20251001"},{equals:"anthropic/claude-haiku-4.5-20251001:beta"},{equals:"anthropic/claude-haiku-4.5:beta"}]},prices:{input_mtok:1,cache_write_mtok:1.25,cache_read_mtok:.1,output_mtok:5}},{id:"anthropic/claude-opus-4",name:"Claude Opus 4",match:{or:[{equals:"anthropic/claude-opus-4"},{equals:"anthropic/claude-opus-4.1"}]},prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"anthropic/claude-opus-4.5",match:{or:[{equals:"anthropic/claude-opus-4.5"},{equals:"anthropic/claude-4.5-opus-20251124"},{equals:"anthropic/claude-4.5-opus-20251124:beta"},{equals:"anthropic/claude-opus-4.5-20251124"},{equals:"anthropic/claude-opus-4.5-20251124:beta"},{equals:"anthropic/claude-opus-4.5:beta"}]},prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"anthropic/claude-opus-4.6",match:{or:[{equals:"anthropic/claude-opus-4.6"},{equals:"anthropic/claude-4.6-opus-20260205"},{equals:"anthropic/claude-4.6-opus-20260205:beta"},{equals:"anthropic/claude-opus-4.6-20260205"},{equals:"anthropic/claude-opus-4.6-20260205:beta"},{equals:"anthropic/claude-opus-4.6:beta"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"anthropic/claude-opus-4.6-fast",name:"Claude Opus 4.6 (Fast)",match:{equals:"anthropic/claude-opus-4.6-fast"},prices:{input_mtok:30,cache_write_mtok:37.5,cache_read_mtok:3,output_mtok:150}},{id:"anthropic/claude-opus-4.7",match:{or:[{equals:"anthropic/claude-opus-4.7"},{equals:"anthropic/claude-opus-4.7:beta"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"anthropic/claude-opus-4.7-fast",name:"Claude Opus 4.7 (Fast)",match:{equals:"anthropic/claude-opus-4.7-fast"},prices:{input_mtok:30,cache_write_mtok:37.5,cache_read_mtok:3,output_mtok:150}},{id:"anthropic/claude-opus-4.8",match:{or:[{equals:"anthropic/claude-opus-4.8"},{equals:"anthropic/claude-opus-4.8:beta"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"anthropic/claude-opus-4.8-fast",name:"Claude Opus 4.8 (Fast)",match:{equals:"anthropic/claude-opus-4.8-fast"},prices:{input_mtok:10,cache_write_mtok:12.5,cache_read_mtok:1,output_mtok:50}},{id:"anthropic/claude-sonnet-4",name:"Claude Sonnet 4",match:{equals:"anthropic/claude-sonnet-4"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"anthropic/claude-sonnet-4.5",match:{or:[{equals:"anthropic/claude-sonnet-4.5"},{equals:"anthropic/claude-4.5-sonnet-20250929"},{equals:"anthropic/claude-4.5-sonnet-20250929:beta"},{equals:"anthropic/claude-sonnet-4.5-20250929"},{equals:"anthropic/claude-sonnet-4.5-20250929:beta"},{equals:"anthropic/claude-sonnet-4.5:beta"}]},context_window:1e6,price_comments:"Tiered pricing: Unlike 4.6 models, Sonnet 4.5 has long-context surcharge. Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:{base:3,tiers:[{start:2e5,price:6}]},cache_write_mtok:{base:3.75,tiers:[{start:2e5,price:7.5}]},cache_read_mtok:{base:.3,tiers:[{start:2e5,price:.6}]},output_mtok:{base:15,tiers:[{start:2e5,price:22.5}]}}},{id:"anthropic/claude-sonnet-4.6",match:{or:[{equals:"anthropic/claude-sonnet-4.6"},{equals:"anthropic/claude-4.6-sonnet-20260217"},{equals:"anthropic/claude-4.6-sonnet-20260217:beta"},{equals:"anthropic/claude-sonnet-4.6-20260217"},{equals:"anthropic/claude-sonnet-4.6-20260217:beta"},{equals:"anthropic/claude-sonnet-4.6:beta"}]},context_window:1e6,price_comments:"Flat pricing across full 1M context window (no tiered pricing). Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing",prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"anubis-pro-105b-v1",name:"Anubis Pro 105B V1",match:{equals:"anubis-pro-105b-v1"},prices:{input_mtok:.8,output_mtok:1}},{id:"arcee-ai/coder-large",name:"Coder Large",match:{equals:"arcee-ai/coder-large"},prices:{input_mtok:.5,output_mtok:.8}},{id:"arcee-ai/trinity-large-thinking",name:"Trinity Large Thinking",match:{equals:"arcee-ai/trinity-large-thinking"},prices:{input_mtok:.22,cache_read_mtok:.06,output_mtok:.85}},{id:"arcee-ai/trinity-mini",name:"Trinity Mini",match:{equals:"arcee-ai/trinity-mini"},prices:{input_mtok:.045,output_mtok:.15}},{id:"arcee-ai/virtuoso-large",name:"Virtuoso Large",match:{equals:"arcee-ai/virtuoso-large"},prices:{input_mtok:.75,output_mtok:1.2}},{id:"arcee-blitz",name:"Arcee Blitz",match:{equals:"arcee-blitz"},prices:{input_mtok:.45,output_mtok:.75}},{id:"arliai/qwq-32b-arliai-rpr-v1:free",match:{equals:"arliai/qwq-32b-arliai-rpr-v1:free"},prices:{}},{id:"baidu/ernie-4.5-vl-424b-a47b",name:"ERNIE 4.5 VL 424B A47B",match:{equals:"baidu/ernie-4.5-vl-424b-a47b"},prices:{input_mtok:.42,output_mtok:1.25}},{id:"bytedance-research/ui-tars-72b:free",match:{equals:"bytedance-research/ui-tars-72b:free"},prices:{}},{id:"bytedance-seed/seed-1.6",name:"Seed 1.6",match:{equals:"bytedance-seed/seed-1.6"},prices:{input_mtok:.25,output_mtok:2}},{id:"bytedance-seed/seed-1.6-flash",name:"Seed 1.6 Flash",match:{equals:"bytedance-seed/seed-1.6-flash"},prices:{input_mtok:.075,output_mtok:.3}},{id:"bytedance-seed/seed-2.0-lite",name:"Seed-2.0-Lite",match:{equals:"bytedance-seed/seed-2.0-lite"},prices:{input_mtok:.25,output_mtok:2}},{id:"bytedance-seed/seed-2.0-mini",name:"Seed-2.0-Mini",match:{equals:"bytedance-seed/seed-2.0-mini"},prices:{input_mtok:.1,output_mtok:.4}},{id:"bytedance/ui-tars-1.5-7b",name:"UI-TARS 7B",match:{equals:"bytedance/ui-tars-1.5-7b"},prices:{input_mtok:.1,cache_read_mtok:.1,output_mtok:.2}},{id:"caller-large",name:"Caller Large",match:{equals:"caller-large"},prices:{input_mtok:.55,output_mtok:.85}},{id:"chatgpt-4o-latest",name:"ChatGPT-4o",match:{equals:"chatgpt-4o-latest"},prices:{input_mtok:5,output_mtok:15}},{id:"claude-2",name:"Claude v2",match:{or:[{equals:"claude-2"},{equals:"claude-2.0"},{equals:"claude-2.0:beta"},{equals:"claude-2.1"},{equals:"claude-2.1:beta"},{equals:"claude-2:beta"}]},prices:{input_mtok:8,output_mtok:24}},{id:"claude-3-opus",name:"Claude 3 Opus",match:{or:[{equals:"claude-3-opus"},{equals:"claude-3-opus:beta"}]},prices:{input_mtok:15,cache_write_mtok:18.75,cache_read_mtok:1.5,output_mtok:75}},{id:"claude-3-sonnet",name:"Claude 3 Sonnet",match:{or:[{equals:"claude-3-sonnet"},{equals:"claude-3-sonnet:beta"}]},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-3.5-sonnet",name:"Claude 3.5 Sonnet",match:{or:[{equals:"claude-3.5-sonnet"},{equals:"claude-3.5-sonnet-20240620"},{equals:"claude-3.5-sonnet-20240620:beta"},{equals:"claude-3.5-sonnet:beta"}]},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"claude-3.7-sonnet",name:"Claude 3.7 Sonnet",match:{or:[{equals:"claude-3.7-sonnet"},{equals:"claude-3.7-sonnet:beta"},{equals:"claude-3.7-sonnet:thinking"}]},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"codellama-7b-instruct-solidity",name:"CodeLLaMa 7B Instruct Solidity",match:{equals:"codellama-7b-instruct-solidity"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"codestral-2501",name:"Codestral 2501",match:{equals:"codestral-2501"},prices:{input_mtok:.3,output_mtok:.9}},{id:"codex-mini",name:"Codex Mini",match:{equals:"codex-mini"},prices:{input_mtok:1.5,cache_read_mtok:.375,output_mtok:6}},{id:"cognitivecomputations/dolphin-mistral-24b-venice-edition:free",name:"Uncensored (free)",match:{equals:"cognitivecomputations/dolphin-mistral-24b-venice-edition:free"},prices:{}},{id:"cognitivecomputations/dolphin-mixtral-8x22b",match:{equals:"cognitivecomputations/dolphin-mixtral-8x22b"},prices:{input_mtok:.9,output_mtok:.9}},{id:"cognitivecomputations/dolphin-mixtral-8x7b",match:{equals:"cognitivecomputations/dolphin-mixtral-8x7b"},prices:{input_mtok:.5,output_mtok:.5}},{id:"cognitivecomputations/dolphin3.0-mistral-24b:free",match:{equals:"cognitivecomputations/dolphin3.0-mistral-24b:free"},prices:{}},{id:"cognitivecomputations/dolphin3.0-r1-mistral-24b:free",match:{equals:"cognitivecomputations/dolphin3.0-r1-mistral-24b:free"},prices:{}},{id:"cohere/command",match:{equals:"cohere/command"},prices:{input_mtok:1,output_mtok:2}},{id:"cohere/command-a",match:{equals:"cohere/command-a"},prices:{input_mtok:2.5,output_mtok:10}},{id:"cohere/command-r",match:{or:[{equals:"cohere/command-r"},{equals:"cohere/command-r-03-2024"}]},prices:{input_mtok:.5,output_mtok:1.5}},{id:"cohere/command-r-08-2024",match:{equals:"cohere/command-r-08-2024"},prices:{input_mtok:.15,output_mtok:.6}},{id:"cohere/command-r-plus",match:{or:[{equals:"cohere/command-r-plus"},{equals:"cohere/command-r-plus-04-2024"}]},prices:{input_mtok:3,output_mtok:15}},{id:"cohere/command-r-plus-08-2024",match:{equals:"cohere/command-r-plus-08-2024"},prices:{input_mtok:2.5,output_mtok:10}},{id:"cohere/command-r7b-12-2024",match:{equals:"cohere/command-r7b-12-2024"},prices:{input_mtok:.0375,output_mtok:.15}},{id:"command",name:"Command",match:{equals:"command"},prices:{input_mtok:1,output_mtok:2}},{id:"command-r",name:"Command R",match:{or:[{equals:"command-r"},{equals:"command-r-03-2024"}]},prices:{input_mtok:.5,output_mtok:1.5}},{id:"command-r-plus",name:"Command R+",match:{or:[{equals:"command-r-plus"},{equals:"command-r-plus-04-2024"}]},prices:{input_mtok:3,output_mtok:15}},{id:"deepcoder-14b-preview:free",name:"Deepcoder 14B Preview (free)",match:{equals:"deepcoder-14b-preview:free"},prices:{}},{id:"deepcogito/cogito-v2.1-671b",name:"Cogito v2.1 671B",match:{equals:"deepcogito/cogito-v2.1-671b"},prices:{input_mtok:1.25,output_mtok:1.25}},{id:"deephermes-3-llama-3-8b-preview:free",name:"DeepHermes 3 Llama 3 8B Preview (free)",match:{equals:"deephermes-3-llama-3-8b-preview:free"},prices:{}},{id:"deepseek-chat-v3-0324:free",name:"DeepSeek V3 0324 (free)",match:{equals:"deepseek-chat-v3-0324:free"},prices:{}},{id:"deepseek-chat:free",name:"DeepSeek V3 (free)",match:{equals:"deepseek-chat:free"},prices:{}},{id:"deepseek-prover-v2",name:"DeepSeek Prover V2",match:{equals:"deepseek-prover-v2"},prices:{input_mtok:.5,output_mtok:2.18}},{id:"deepseek-r1-0528-qwen3-8b",name:"Deepseek R1 0528 Qwen3 8B",match:{equals:"deepseek-r1-0528-qwen3-8b"},prices:{input_mtok:.05,output_mtok:.1}},{id:"deepseek-r1-0528-qwen3-8b:free",name:"Deepseek R1 0528 Qwen3 8B (free)",match:{equals:"deepseek-r1-0528-qwen3-8b:free"},prices:{}},{id:"deepseek-r1-0528:free",name:"R1 0528 (free)",match:{equals:"deepseek-r1-0528:free"},prices:{}},{id:"deepseek-r1-distill-llama-70b:free",name:"R1 Distill Llama 70B (free)",match:{equals:"deepseek-r1-distill-llama-70b:free"},prices:{}},{id:"deepseek-r1-distill-llama-8b",name:"R1 Distill Llama 8B",match:{equals:"deepseek-r1-distill-llama-8b"},prices:{input_mtok:.04,output_mtok:.04}},{id:"deepseek-r1-distill-qwen-1.5b",name:"R1 Distill Qwen 1.5B",match:{equals:"deepseek-r1-distill-qwen-1.5b"},prices:{input_mtok:.18,output_mtok:.18}},{id:"deepseek-r1-distill-qwen-14b",name:"R1 Distill Qwen 14B",match:{equals:"deepseek-r1-distill-qwen-14b"},prices:{input_mtok:.15,output_mtok:.15}},{id:"deepseek-r1-distill-qwen-14b:free",name:"R1 Distill Qwen 14B (free)",match:{equals:"deepseek-r1-distill-qwen-14b:free"},prices:{}},{id:"deepseek-r1-distill-qwen-32b:free",name:"R1 Distill Qwen 32B (free)",match:{equals:"deepseek-r1-distill-qwen-32b:free"},prices:{}},{id:"deepseek-r1-distill-qwen-7b",name:"R1 Distill Qwen 7B",match:{equals:"deepseek-r1-distill-qwen-7b"},prices:{input_mtok:.1,output_mtok:.2}},{id:"deepseek-r1:free",name:"R1 (free)",match:{equals:"deepseek-r1:free"},prices:{}},{id:"deepseek-r1t-chimera:free",name:"DeepSeek R1T Chimera (free)",match:{equals:"deepseek-r1t-chimera:free"},prices:{}},{id:"deepseek-v3-base:free",name:"DeepSeek V3 Base (free)",match:{equals:"deepseek-v3-base:free"},prices:{}},{id:"deepseek/deepseek-chat",name:"DeepSeek V3",match:{equals:"deepseek/deepseek-chat"},prices:{input_mtok:.38,output_mtok:.89}},{id:"deepseek/deepseek-chat-v3-0324",name:"DeepSeek V3 0324",match:{equals:"deepseek/deepseek-chat-v3-0324"},prices:{input_mtok:.3,output_mtok:.88}},{id:"deepseek/deepseek-chat-v3-0324:free",match:{equals:"deepseek/deepseek-chat-v3-0324:free"},prices:{}},{id:"deepseek/deepseek-chat-v3.1",name:"DeepSeek V3.1",match:{equals:"deepseek/deepseek-chat-v3.1"},prices:{input_mtok:.21,cache_read_mtok:.13,output_mtok:.79}},{id:"deepseek/deepseek-chat:free",match:{equals:"deepseek/deepseek-chat:free"},prices:{}},{id:"deepseek/deepseek-r1",name:"R1",match:{equals:"deepseek/deepseek-r1"},prices:{input_mtok:.45,output_mtok:2.15}},{id:"deepseek/deepseek-r1-0528",name:"R1 0528",match:{equals:"deepseek/deepseek-r1-0528"},prices:{input_mtok:.5,output_mtok:2.15}},{id:"deepseek/deepseek-r1-distill-llama-70b",name:"R1 Distill Llama 70B",match:{equals:"deepseek/deepseek-r1-distill-llama-70b"},prices:{input_mtok:.1,output_mtok:.4}},{id:"deepseek/deepseek-r1-distill-llama-70b:free",match:{equals:"deepseek/deepseek-r1-distill-llama-70b:free"},prices:{}},{id:"deepseek/deepseek-r1-distill-llama-8b",match:{equals:"deepseek/deepseek-r1-distill-llama-8b"},prices:{input_mtok:.04,output_mtok:.04}},{id:"deepseek/deepseek-r1-distill-qwen-1.5b",match:{equals:"deepseek/deepseek-r1-distill-qwen-1.5b"},prices:{input_mtok:.18,output_mtok:.18}},{id:"deepseek/deepseek-r1-distill-qwen-14b",match:{equals:"deepseek/deepseek-r1-distill-qwen-14b"},prices:{input_mtok:.15,output_mtok:.15}},{id:"deepseek/deepseek-r1-distill-qwen-14b:free",match:{equals:"deepseek/deepseek-r1-distill-qwen-14b:free"},prices:{}},{id:"deepseek/deepseek-r1-distill-qwen-32b",name:"R1 Distill Qwen 32B",match:{equals:"deepseek/deepseek-r1-distill-qwen-32b"},prices:{input_mtok:.12,output_mtok:.18}},{id:"deepseek/deepseek-r1-distill-qwen-32b:free",match:{equals:"deepseek/deepseek-r1-distill-qwen-32b:free"},prices:{}},{id:"deepseek/deepseek-r1-zero:free",match:{equals:"deepseek/deepseek-r1-zero:free"},prices:{}},{id:"deepseek/deepseek-r1:free",match:{equals:"deepseek/deepseek-r1:free"},prices:{}},{id:"deepseek/deepseek-v3-base:free",match:{equals:"deepseek/deepseek-v3-base:free"},prices:{}},{id:"deepseek/deepseek-v3.1-terminus",name:"DeepSeek V3.1 Terminus",match:{equals:"deepseek/deepseek-v3.1-terminus"},context_window:163840,prices:{input_mtok:.23,output_mtok:.9}},{id:"deepseek/deepseek-v3.2",name:"DeepSeek V3.2",match:{equals:"deepseek/deepseek-v3.2"},prices:{input_mtok:.2288,output_mtok:.3432}},{id:"deepseek/deepseek-v3.2-exp",name:"DeepSeek V3.2 Exp",match:{equals:"deepseek/deepseek-v3.2-exp"},prices:{input_mtok:.27,output_mtok:.41}},{id:"deepseek/deepseek-v4-flash",name:"DeepSeek V4 Flash",match:{equals:"deepseek/deepseek-v4-flash"},prices:{input_mtok:.0983,cache_read_mtok:.0197,output_mtok:.1966}},{id:"deepseek/deepseek-v4-pro",name:"DeepSeek V4 Pro",match:{equals:"deepseek/deepseek-v4-pro"},prices:{input_mtok:.435,cache_read_mtok:.003625,output_mtok:.87}},{id:"devstral-small",name:"Devstral Small",match:{equals:"devstral-small"},prices:{input_mtok:.06,output_mtok:.12}},{id:"devstral-small:free",name:"Devstral Small (free)",match:{equals:"devstral-small:free"},prices:{}},{id:"dobby-mini-unhinged-plus-llama-3.1-8b",name:"Dobby Mini Plus Llama 3.1 8B",match:{equals:"dobby-mini-unhinged-plus-llama-3.1-8b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"dolphin-mixtral-8x22b",name:"Dolphin 2.9.2 Mixtral 8x22B 🐬",match:{equals:"dolphin-mixtral-8x22b"},prices:{input_mtok:.9,output_mtok:.9}},{id:"dolphin3.0-mistral-24b:free",name:"Dolphin3.0 Mistral 24B (free)",match:{equals:"dolphin3.0-mistral-24b:free"},prices:{}},{id:"dolphin3.0-r1-mistral-24b:free",name:"Dolphin3.0 R1 Mistral 24B (free)",match:{equals:"dolphin3.0-r1-mistral-24b:free"},prices:{}},{id:"eleutherai/llemma_7b",match:{equals:"eleutherai/llemma_7b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"essentialai/rnj-1-instruct",name:"Rnj 1 Instruct",match:{equals:"essentialai/rnj-1-instruct"},prices:{input_mtok:.15,output_mtok:.15}},{id:"eva-llama-3.33-70b",name:"EVA Llama 3.33 70B",match:{equals:"eva-llama-3.33-70b"},prices:{input_mtok:4,output_mtok:6}},{id:"eva-qwen-2.5-32b",name:"EVA Qwen2.5 32B",match:{equals:"eva-qwen-2.5-32b"},prices:{input_mtok:2.6,output_mtok:3.4}},{id:"eva-qwen-2.5-72b",name:"EVA Qwen2.5 72B",match:{equals:"eva-qwen-2.5-72b"},prices:{input_mtok:4,output_mtok:6}},{id:"eva-unit-01/eva-llama-3.33-70b",match:{equals:"eva-unit-01/eva-llama-3.33-70b"},prices:{input_mtok:4,output_mtok:6}},{id:"eva-unit-01/eva-qwen-2.5-32b",match:{equals:"eva-unit-01/eva-qwen-2.5-32b"},prices:{input_mtok:2.6,output_mtok:3.4}},{id:"eva-unit-01/eva-qwen-2.5-72b",match:{equals:"eva-unit-01/eva-qwen-2.5-72b"},prices:{input_mtok:.9,output_mtok:1.2}},{id:"featherless/qwerky-72b:free",match:{equals:"featherless/qwerky-72b:free"},prices:{}},{id:"fimbulvetr-11b-v2",name:"Fimbulvetr 11B v2",match:{equals:"fimbulvetr-11b-v2"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"gemini-2.0-flash-001",name:"Gemini 2.0 Flash",match:{equals:"gemini-2.0-flash-001"},prices:{input_mtok:.1,cache_write_mtok:.1833,cache_read_mtok:.025,output_mtok:.4}},{id:"gemini-2.0-flash-exp:free",name:"Gemini 2.0 Flash Experimental (free)",match:{equals:"gemini-2.0-flash-exp:free"},prices:{}},{id:"gemini-2.0-flash-lite-001",name:"Gemini 2.0 Flash Lite",match:{equals:"gemini-2.0-flash-lite-001"},prices:{input_mtok:.075,output_mtok:.3}},{id:"gemini-2.5-flash-lite-preview-06-17",name:"Gemini 2.5 Flash Lite Preview 06-17",match:{equals:"gemini-2.5-flash-lite-preview-06-17"},prices:{input_mtok:.1,output_mtok:.4}},{id:"gemini-2.5-flash-preview",name:"Gemini 2.5 Flash Preview 04-17",match:{or:[{equals:"gemini-2.5-flash-preview"},{equals:"gemini-2.5-flash-preview-05-20"}]},prices:{input_mtok:.15,cache_write_mtok:.2333,cache_read_mtok:.0375,output_mtok:.6}},{id:"gemini-2.5-flash-preview-05-20:thinking",name:"Gemini 2.5 Flash Preview 05-20 (thinking)",match:{equals:"gemini-2.5-flash-preview-05-20:thinking"},prices:{input_mtok:.15,cache_write_mtok:.2333,cache_read_mtok:.0375,output_mtok:3.5}},{id:"gemini-2.5-flash-preview:thinking",name:"Gemini 2.5 Flash Preview 04-17 (thinking)",match:{equals:"gemini-2.5-flash-preview:thinking"},prices:{input_mtok:.15,cache_write_mtok:.2333,cache_read_mtok:.0375,output_mtok:3.5}},{id:"gemini-2.5-pro-exp-03-25",name:"Gemini 2.5 Pro Experimental",match:{equals:"gemini-2.5-pro-exp-03-25"},prices:{}},{id:"gemini-flash-1.5",name:"Gemini 1.5 Flash",match:{equals:"gemini-flash-1.5"},prices:{input_mtok:.075,cache_write_mtok:.1583,cache_read_mtok:.01875,output_mtok:.3}},{id:"gemini-flash-1.5-8b",name:"Gemini 1.5 Flash 8B",match:{equals:"gemini-flash-1.5-8b"},prices:{input_mtok:.0375,cache_write_mtok:.0583,cache_read_mtok:.01,output_mtok:.15}},{id:"gemini-pro-1.5",name:"Gemini 1.5 Pro",match:{equals:"gemini-pro-1.5"},prices:{input_mtok:1.25,output_mtok:5}},{id:"gemma-2-9b-it",name:"Gemma 2 9B",match:{equals:"gemma-2-9b-it"},prices:{input_mtok:.2,output_mtok:.2}},{id:"gemma-2-9b-it:free",name:"Gemma 2 9B (free)",match:{equals:"gemma-2-9b-it:free"},prices:{}},{id:"gemma-3-12b-it:free",name:"Gemma 3 12B (free)",match:{equals:"gemma-3-12b-it:free"},prices:{}},{id:"gemma-3-27b-it:free",name:"Gemma 3 27B (free)",match:{equals:"gemma-3-27b-it:free"},prices:{}},{id:"gemma-3-4b-it:free",name:"Gemma 3 4B (free)",match:{equals:"gemma-3-4b-it:free"},prices:{}},{id:"gemma-3n-e4b-it:free",name:"Gemma 3n 4B (free)",match:{equals:"gemma-3n-e4b-it:free"},prices:{}},{id:"glm-4-32b",name:"GLM 4 32B",match:{equals:"glm-4-32b"},prices:{input_mtok:.24,output_mtok:.24}},{id:"glm-4-32b:free",name:"GLM 4 32B (free)",match:{equals:"glm-4-32b:free"},prices:{}},{id:"glm-4.5-air:free",name:"GLM 4.5 Air (free)",match:{equals:"glm-4.5-air:free"},prices:{}},{id:"glm-5v-turbo",name:"GLM 5V Turbo",match:{equals:"glm-5v-turbo"},prices:{input_mtok:1.2,cache_read_mtok:.24,output_mtok:4}},{id:"glm-z1-32b",name:"GLM Z1 32B",match:{equals:"glm-z1-32b"},prices:{input_mtok:.24,output_mtok:.24}},{id:"glm-z1-32b:free",name:"GLM Z1 32B (free)",match:{equals:"glm-z1-32b:free"},prices:{}},{id:"glm-z1-rumination-32b",name:"GLM Z1 Rumination 32B",match:{equals:"glm-z1-rumination-32b"},prices:{input_mtok:.24,output_mtok:.24}},{id:"goliath-120b",name:"Goliath 120B",match:{equals:"goliath-120b"},prices:{input_mtok:10,output_mtok:12.5}},{id:"google/gemini-2.0-flash-001",match:{equals:"google/gemini-2.0-flash-001"},prices:{input_mtok:.1,output_mtok:.4}},{id:"google/gemini-2.0-flash-exp:free",match:{equals:"google/gemini-2.0-flash-exp:free"},prices:{}},{id:"google/gemini-2.0-flash-lite-001",match:{equals:"google/gemini-2.0-flash-lite-001"},prices:{input_mtok:.075,output_mtok:.3}},{id:"google/gemini-2.0-flash-thinking-exp-1219:free",match:{equals:"google/gemini-2.0-flash-thinking-exp-1219:free"},prices:{}},{id:"google/gemini-2.0-flash-thinking-exp:free",match:{equals:"google/gemini-2.0-flash-thinking-exp:free"},prices:{}},{id:"google/gemini-2.5-flash",name:"Gemini 2.5 Flash",match:{equals:"google/gemini-2.5-flash"},prices:{input_mtok:.3,cache_write_mtok:.3833,cache_read_mtok:.075,output_mtok:2.5}},{id:"google/gemini-2.5-flash-image",name:"Nano Banana (Gemini 2.5 Flash Image)",match:{equals:"google/gemini-2.5-flash-image"},prices:{input_mtok:.3,cache_write_mtok:.08333333333333334,cache_read_mtok:.03,output_mtok:2.5}},{id:"google/gemini-2.5-flash-lite",name:"Gemini 2.5 Flash Lite",match:{equals:"google/gemini-2.5-flash-lite"},prices:{input_mtok:.1,cache_write_mtok:.08333333333333334,cache_read_mtok:.01,output_mtok:.4}},{id:"google/gemini-2.5-flash-lite-preview-09-2025",name:"Gemini 2.5 Flash Lite Preview 09-2025",match:{equals:"google/gemini-2.5-flash-lite-preview-09-2025"},prices:{input_mtok:.1,output_mtok:.4}},{id:"google/gemini-2.5-flash-preview",match:{equals:"google/gemini-2.5-flash-preview"},prices:{input_mtok:.15,output_mtok:.6}},{id:"google/gemini-2.5-flash-preview-09-2025",name:"Gemini 2.5 Flash Preview 09-2025",match:{equals:"google/gemini-2.5-flash-preview-09-2025"},prices:{input_mtok:.3,cache_write_mtok:.383,cache_read_mtok:.075,output_mtok:2.5}},{id:"google/gemini-2.5-flash-preview:thinking",match:{equals:"google/gemini-2.5-flash-preview:thinking"},prices:{input_mtok:.15,output_mtok:3.5}},{id:"google/gemini-2.5-pro",name:"Gemini 2.5 Pro",match:{or:[{equals:"google/gemini-2.5-pro"},{equals:"google/gemini-2.5-pro-preview"},{equals:"google/gemini-2.5-pro-preview-05-06"}]},prices:{input_mtok:1.25,cache_write_mtok:1.625,cache_read_mtok:.31,output_mtok:10}},{id:"google/gemini-2.5-pro-exp-03-25:free",match:{equals:"google/gemini-2.5-pro-exp-03-25:free"},prices:{}},{id:"google/gemini-2.5-pro-preview-03-25",match:{equals:"google/gemini-2.5-pro-preview-03-25"},prices:{input_mtok:1.25,output_mtok:10}},{id:"google/gemini-3-flash-preview",name:"Gemini 3 Flash Preview",match:{equals:"google/gemini-3-flash-preview"},prices:{input_mtok:.5,cache_write_mtok:.08333333333333334,cache_read_mtok:.05,output_mtok:3}},{id:"google/gemini-3-pro-image-preview",name:"Nano Banana Pro (Gemini 3 Pro Image Preview)",match:{equals:"google/gemini-3-pro-image-preview"},prices:{input_mtok:2,cache_write_mtok:.375,cache_read_mtok:.2,output_mtok:12}},{id:"google/gemini-3.1-flash-image-preview",name:"Nano Banana 2 (Gemini 3.1 Flash Image Preview)",match:{equals:"google/gemini-3.1-flash-image-preview"},prices:{input_mtok:.5,output_mtok:3}},{id:"google/gemini-3.1-flash-lite",name:"Gemini 3.1 Flash Lite",match:{or:[{equals:"google/gemini-3.1-flash-lite"},{equals:"google/gemini-3.1-flash-lite-preview"}]},prices:{input_mtok:.25,cache_write_mtok:.08333333333333334,cache_read_mtok:.025,output_mtok:1.5}},{id:"google/gemini-3.1-pro-preview",name:"Gemini 3.1 Pro Preview",match:{or:[{equals:"google/gemini-3.1-pro-preview"},{equals:"google/gemini-3.1-pro-preview-customtools"}]},prices:{input_mtok:2,cache_write_mtok:.375,cache_read_mtok:.2,output_mtok:12}},{id:"google/gemini-3.5-flash",name:"Gemini 3.5 Flash",match:{equals:"google/gemini-3.5-flash"},prices:{input_mtok:1.5,cache_write_mtok:.08333333333333334,cache_read_mtok:.15,output_mtok:9}},{id:"google/gemini-flash-1.5",match:{equals:"google/gemini-flash-1.5"},prices:{input_mtok:.075,output_mtok:.3}},{id:"google/gemini-flash-1.5-8b",match:{equals:"google/gemini-flash-1.5-8b"},prices:{input_mtok:.0375,output_mtok:.15}},{id:"google/gemini-flash-1.5-8b-exp",match:{equals:"google/gemini-flash-1.5-8b-exp"},prices:{}},{id:"google/gemini-pro",match:{or:[{equals:"google/gemini-pro"},{equals:"google/gemini-pro-vision"}]},prices:{input_mtok:.5,output_mtok:1.5}},{id:"google/gemini-pro-1.5",match:{equals:"google/gemini-pro-1.5"},prices:{input_mtok:1.25,output_mtok:5}},{id:"google/gemma-2-27b-it",name:"Gemma 2 27B",match:{equals:"google/gemma-2-27b-it"},prices:{input_mtok:.8,output_mtok:.8}},{id:"google/gemma-2-9b-it",match:{equals:"google/gemma-2-9b-it"},prices:{input_mtok:.07,output_mtok:.07}},{id:"google/gemma-2-9b-it:free",match:{equals:"google/gemma-2-9b-it:free"},prices:{}},{id:"google/gemma-3-12b-it",name:"Gemma 3 12B",match:{equals:"google/gemma-3-12b-it"},prices:{input_mtok:.05,output_mtok:.1}},{id:"google/gemma-3-12b-it:free",match:{equals:"google/gemma-3-12b-it:free"},prices:{}},{id:"google/gemma-3-1b-it:free",match:{equals:"google/gemma-3-1b-it:free"},prices:{}},{id:"google/gemma-3-27b-it",name:"Gemma 3 27B",match:{equals:"google/gemma-3-27b-it"},prices:{input_mtok:.1,output_mtok:.2}},{id:"google/gemma-3-27b-it:free",match:{equals:"google/gemma-3-27b-it:free"},prices:{}},{id:"google/gemma-3-4b-it",name:"Gemma 3 4B",match:{equals:"google/gemma-3-4b-it"},prices:{input_mtok:.02,output_mtok:.04}},{id:"google/gemma-3-4b-it:free",match:{equals:"google/gemma-3-4b-it:free"},prices:{}},{id:"google/gemma-3n-e4b-it",name:"Gemma 3n 4B",match:{equals:"google/gemma-3n-e4b-it"},prices:{input_mtok:.06,output_mtok:.12}},{id:"google/gemma-4-26b-a4b-it",name:"Gemma 4 26B A4B",match:{equals:"google/gemma-4-26b-a4b-it"},prices:{input_mtok:.06,output_mtok:.33}},{id:"google/gemma-4-26b-a4b-it:free",name:"Gemma 4 26B A4B (free)",match:{equals:"google/gemma-4-26b-a4b-it:free"},prices:{}},{id:"google/gemma-4-31b-it",name:"Gemma 4 31B",match:{equals:"google/gemma-4-31b-it"},prices:{input_mtok:.12,cache_read_mtok:.09,output_mtok:.36}},{id:"google/gemma-4-31b-it:free",name:"Gemma 4 31B (free)",match:{equals:"google/gemma-4-31b-it:free"},prices:{}},{id:"google/learnlm-1.5-pro-experimental:free",match:{equals:"google/learnlm-1.5-pro-experimental:free"},prices:{}},{id:"google/lyria-3-clip-preview",name:"Lyria 3 Clip Preview",match:{equals:"google/lyria-3-clip-preview"},prices:{}},{id:"google/lyria-3-pro-preview",name:"Lyria 3 Pro Preview",match:{equals:"google/lyria-3-pro-preview"},prices:{}},{id:"google/palm-2-chat-bison",match:{or:[{equals:"google/palm-2-chat-bison"},{equals:"google/palm-2-chat-bison-32k"}]},prices:{input_mtok:1,output_mtok:2}},{id:"google/palm-2-codechat-bison",match:{or:[{equals:"google/palm-2-codechat-bison"},{equals:"google/palm-2-codechat-bison-32k"}]},prices:{input_mtok:1,output_mtok:2}},{id:"gpt-3.5-turbo-1106",name:"GPT-3.5 Turbo 16k (older v1106)",match:{equals:"gpt-3.5-turbo-1106"},prices:{input_mtok:1,output_mtok:2}},{id:"gpt-4-1106-preview",name:"GPT-4 Turbo (older v1106)",match:{equals:"gpt-4-1106-preview"},prices:{input_mtok:10,output_mtok:30}},{id:"gpt-4.5-preview",name:"GPT-4.5 (Preview)",match:{equals:"gpt-4.5-preview"},prices:{input_mtok:75,cache_read_mtok:37.5,output_mtok:150}},{id:"gpt-4o:extended",name:"GPT-4o (extended)",match:{equals:"gpt-4o:extended"},prices:{input_mtok:6,output_mtok:18}},{id:"grok-2-1212",name:"Grok 2 1212",match:{equals:"grok-2-1212"},prices:{input_mtok:2,output_mtok:10}},{id:"grok-2-vision-1212",name:"Grok 2 Vision 1212",match:{equals:"grok-2-vision-1212"},prices:{input_mtok:2,output_mtok:10}},{id:"grok-3",name:"Grok 3",match:{or:[{equals:"grok-3"},{equals:"grok-3-beta"}]},prices:{input_mtok:3,cache_read_mtok:.75,output_mtok:15}},{id:"grok-3-mini",name:"Grok 3 Mini",match:{or:[{equals:"grok-3-mini"},{equals:"grok-3-mini-beta"}]},prices:{input_mtok:.3,cache_read_mtok:.075,output_mtok:.5}},{id:"grok-beta",name:"Grok Beta",match:{equals:"grok-beta"},prices:{input_mtok:5,output_mtok:15}},{id:"grok-vision-beta",name:"Grok Vision Beta",match:{equals:"grok-vision-beta"},prices:{input_mtok:5,output_mtok:15}},{id:"gryphe/mythomax-l2-13b",match:{equals:"gryphe/mythomax-l2-13b"},prices:{input_mtok:.065,output_mtok:.065}},{id:"hermes-2-pro-llama-3-8b",name:"Hermes 2 Pro - Llama-3 8B",match:{equals:"hermes-2-pro-llama-3-8b"},prices:{input_mtok:.025,output_mtok:.04}},{id:"huggingfaceh4/zephyr-7b-beta:free",match:{equals:"huggingfaceh4/zephyr-7b-beta:free"},prices:{}},{id:"ibm-granite/granite-4.0-h-micro",name:"Granite 4.0 Micro",match:{equals:"ibm-granite/granite-4.0-h-micro"},prices:{input_mtok:.017,output_mtok:.112}},{id:"ibm-granite/granite-4.1-8b",name:"Granite 4.1 8B",match:{equals:"ibm-granite/granite-4.1-8b"},prices:{input_mtok:.05,cache_read_mtok:.05,output_mtok:.1}},{id:"inception/mercury-2",name:"Mercury 2",match:{equals:"inception/mercury-2"},prices:{input_mtok:.25,cache_read_mtok:.025,output_mtok:.75}},{id:"inclusionai/ling-2.6-1t",name:"Ling-2.6-1T",match:{equals:"inclusionai/ling-2.6-1t"},prices:{input_mtok:.075,cache_read_mtok:.015,output_mtok:.625}},{id:"inclusionai/ling-2.6-flash",name:"Ling-2.6-flash",match:{equals:"inclusionai/ling-2.6-flash"},prices:{input_mtok:.01,cache_read_mtok:.002,output_mtok:.03}},{id:"inclusionai/ring-2.6-1t",name:"Ring-2.6-1T",match:{equals:"inclusionai/ring-2.6-1t"},prices:{input_mtok:.075,cache_read_mtok:.015,output_mtok:.625}},{id:"infermatic/mn-inferor-12b",match:{equals:"infermatic/mn-inferor-12b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"inflection/inflection-3-pi",name:"Inflection 3 Pi",match:{equals:"inflection/inflection-3-pi"},prices:{input_mtok:2.5,output_mtok:10}},{id:"inflection/inflection-3-productivity",name:"Inflection 3 Productivity",match:{equals:"inflection/inflection-3-productivity"},prices:{input_mtok:2.5,output_mtok:10}},{id:"internvl3-14b:free",name:"InternVL3 14B (free)",match:{equals:"internvl3-14b:free"},prices:{}},{id:"internvl3-2b:free",name:"InternVL3 2B (free)",match:{equals:"internvl3-2b:free"},prices:{}},{id:"jamba-1.6-large",name:"Jamba 1.6 Large",match:{equals:"jamba-1.6-large"},prices:{input_mtok:2,output_mtok:8}},{id:"jamba-1.6-mini",name:"Jamba Mini 1.6",match:{equals:"jamba-1.6-mini"},prices:{input_mtok:.2,output_mtok:.4}},{id:"jondurbin/airoboros-l2-70b",match:{equals:"jondurbin/airoboros-l2-70b"},prices:{input_mtok:.5,output_mtok:.5}},{id:"kimi-dev-72b:free",name:"Kimi Dev 72b (free)",match:{equals:"kimi-dev-72b:free"},prices:{}},{id:"kimi-vl-a3b-thinking:free",name:"Kimi VL A3B Thinking (free)",match:{equals:"kimi-vl-a3b-thinking:free"},prices:{}},{id:"kwaipilot/kat-coder-pro-v2",name:"KAT-Coder-Pro V2",match:{equals:"kwaipilot/kat-coder-pro-v2"},prices:{input_mtok:.3,cache_read_mtok:.06,output_mtok:1.2}},{id:"l3-euryale-70b",name:"Llama 3 Euryale 70B v2.1",match:{equals:"l3-euryale-70b"},prices:{input_mtok:1.48,output_mtok:1.48}},{id:"latitudegames/wayfarer-large-70b-llama-3.3",match:{equals:"latitudegames/wayfarer-large-70b-llama-3.3"},prices:{input_mtok:.8,output_mtok:.9}},{id:"lfm-3b",name:"LFM 3B",match:{equals:"lfm-3b"},prices:{input_mtok:.02,output_mtok:.02}},{id:"lfm-40b",name:"LFM 40B MoE",match:{equals:"lfm-40b"},prices:{input_mtok:.15,output_mtok:.15}},{id:"lfm-7b",name:"LFM 7B",match:{equals:"lfm-7b"},prices:{input_mtok:.01,output_mtok:.01}},{id:"liquid/lfm-2-24b-a2b",name:"LFM2-24B-A2B",match:{equals:"liquid/lfm-2-24b-a2b"},prices:{input_mtok:.03,output_mtok:.12}},{id:"liquid/lfm-2.5-1.2b-instruct:free",name:"LFM2.5-1.2B-Instruct (free)",match:{equals:"liquid/lfm-2.5-1.2b-instruct:free"},prices:{}},{id:"liquid/lfm-2.5-1.2b-thinking:free",name:"LFM2.5-1.2B-Thinking (free)",match:{equals:"liquid/lfm-2.5-1.2b-thinking:free"},prices:{}},{id:"liquid/lfm-3b",match:{equals:"liquid/lfm-3b"},prices:{input_mtok:.02,output_mtok:.02}},{id:"liquid/lfm-40b",match:{equals:"liquid/lfm-40b"},prices:{input_mtok:.15,output_mtok:.15}},{id:"liquid/lfm-7b",match:{equals:"liquid/lfm-7b"},prices:{input_mtok:.01,output_mtok:.01}},{id:"llama-3-lumimaid-70b",name:"Llama 3 Lumimaid 70B",match:{equals:"llama-3-lumimaid-70b"},prices:{input_mtok:4,output_mtok:6}},{id:"llama-3-lumimaid-8b",name:"Llama 3 Lumimaid 8B",match:{equals:"llama-3-lumimaid-8b"},prices:{input_mtok:.2,output_mtok:1.25}},{id:"llama-3.1-405b",name:"Llama 3.1 405B (base)",match:{equals:"llama-3.1-405b"},prices:{input_mtok:2,output_mtok:2}},{id:"llama-3.1-405b-instruct",name:"Llama 3.1 405B Instruct",match:{equals:"llama-3.1-405b-instruct"},prices:{input_mtok:.8,output_mtok:.8}},{id:"llama-3.1-8b-instruct:free",name:"Llama 3.1 8B Instruct (free)",match:{equals:"llama-3.1-8b-instruct:free"},prices:{}},{id:"llama-3.1-lumimaid-70b",name:"Lumimaid v0.2 70B",match:{equals:"llama-3.1-lumimaid-70b"},prices:{input_mtok:2.5,output_mtok:3}},{id:"llama-3.1-lumimaid-8b",name:"Lumimaid v0.2 8B",match:{equals:"llama-3.1-lumimaid-8b"},prices:{input_mtok:.2,output_mtok:1.25}},{id:"llama-3.1-nemotron-70b-instruct",name:"Llama 3.1 Nemotron 70B Instruct",match:{equals:"llama-3.1-nemotron-70b-instruct"},prices:{input_mtok:.12,output_mtok:.3}},{id:"llama-3.1-nemotron-ultra-253b-v1",name:"Llama 3.1 Nemotron Ultra 253B v1",match:{equals:"llama-3.1-nemotron-ultra-253b-v1"},prices:{input_mtok:.6,output_mtok:1.8}},{id:"llama-3.1-nemotron-ultra-253b-v1:free",name:"Llama 3.1 Nemotron Ultra 253B v1 (free)",match:{equals:"llama-3.1-nemotron-ultra-253b-v1:free"},prices:{}},{id:"llama-3.1-sonar-large-128k-online",name:"Llama 3.1 Sonar 70B Online",match:{equals:"llama-3.1-sonar-large-128k-online"},prices:{input_mtok:1,output_mtok:1}},{id:"llama-3.1-sonar-small-128k-online",name:"Llama 3.1 Sonar 8B Online",match:{equals:"llama-3.1-sonar-small-128k-online"},prices:{input_mtok:.2,output_mtok:.2}},{id:"llama-3.2-11b-vision-instruct:free",name:"Llama 3.2 11B Vision Instruct (free)",match:{equals:"llama-3.2-11b-vision-instruct:free"},prices:{}},{id:"llama-3.2-1b-instruct:free",name:"Llama 3.2 1B Instruct (free)",match:{equals:"llama-3.2-1b-instruct:free"},prices:{}},{id:"llama-3.2-90b-vision-instruct",name:"Llama 3.2 90B Vision Instruct",match:{equals:"llama-3.2-90b-vision-instruct"},prices:{input_mtok:1.2,output_mtok:1.2}},{id:"llama-3.3-8b-instruct:free",name:"Llama 3.3 8B Instruct (free)",match:{equals:"llama-3.3-8b-instruct:free"},prices:{}},{id:"llama-3.3-nemotron-super-49b-v1",name:"Llama 3.3 Nemotron Super 49B v1",match:{equals:"llama-3.3-nemotron-super-49b-v1"},prices:{input_mtok:.13,output_mtok:.4}},{id:"llama-3.3-nemotron-super-49b-v1:free",name:"Llama 3.3 Nemotron Super 49B v1 (free)",match:{equals:"llama-3.3-nemotron-super-49b-v1:free"},prices:{}},{id:"llama-4-maverick:free",name:"Llama 4 Maverick (free)",match:{equals:"llama-4-maverick:free"},prices:{}},{id:"llama-4-scout:free",name:"Llama 4 Scout (free)",match:{equals:"llama-4-scout:free"},prices:{}},{id:"llama-guard-2-8b",name:"LlamaGuard 2 8B",match:{equals:"llama-guard-2-8b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"llama3.1-typhoon2-70b-instruct",name:"Typhoon2 70B Instruct",match:{equals:"llama3.1-typhoon2-70b-instruct"},prices:{input_mtok:.88,output_mtok:.88}},{id:"llemma_7b",name:"Llemma 7b",match:{equals:"llemma_7b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"maestro-reasoning",name:"Maestro Reasoning",match:{equals:"maestro-reasoning"},prices:{input_mtok:.9,output_mtok:3.3}},{id:"magistral-medium-2506",name:"Magistral Medium 2506",match:{or:[{equals:"magistral-medium-2506"},{equals:"magistral-medium-2506:thinking"}]},prices:{input_mtok:2,output_mtok:5}},{id:"magistral-small-2506",name:"Magistral Small 2506",match:{equals:"magistral-small-2506"},prices:{input_mtok:.5,output_mtok:1.5}},{id:"magnum-72b",name:"Magnum 72B",match:{equals:"magnum-72b"},prices:{input_mtok:4,output_mtok:6}},{id:"magnum-v2-72b",name:"Magnum v2 72B",match:{equals:"magnum-v2-72b"},prices:{input_mtok:3,output_mtok:3}},{id:"mai-ds-r1:free",name:"MAI DS R1 (free)",match:{equals:"mai-ds-r1:free"},prices:{}},{id:"mancer/weaver",match:{equals:"mancer/weaver"},prices:{input_mtok:1.125,output_mtok:1.125}},{id:"mercury-coder-small-beta",name:"Mercury Coder Small Beta",match:{equals:"mercury-coder-small-beta"},prices:{input_mtok:.25,output_mtok:1}},{id:"meta-llama/llama-2-13b-chat",match:{equals:"meta-llama/llama-2-13b-chat"},prices:{input_mtok:.22,output_mtok:.22}},{id:"meta-llama/llama-2-70b-chat",match:{equals:"meta-llama/llama-2-70b-chat"},prices:{input_mtok:.9,output_mtok:.9}},{id:"meta-llama/llama-3-70b-instruct",name:"Llama 3 70B Instruct",match:{equals:"meta-llama/llama-3-70b-instruct"},prices:{input_mtok:.3,output_mtok:.4}},{id:"meta-llama/llama-3-8b-instruct",name:"Llama 3 8B Instruct",match:{equals:"meta-llama/llama-3-8b-instruct"},prices:{input_mtok:.03,output_mtok:.06}},{id:"meta-llama/llama-3.1-405b",match:{equals:"meta-llama/llama-3.1-405b"},prices:{input_mtok:2,output_mtok:2}},{id:"meta-llama/llama-3.1-405b-instruct",match:{equals:"meta-llama/llama-3.1-405b-instruct"},prices:{input_mtok:.8,output_mtok:.8}},{id:"meta-llama/llama-3.1-405b:free",match:{equals:"meta-llama/llama-3.1-405b:free"},prices:{}},{id:"meta-llama/llama-3.1-70b-instruct",name:"Llama 3.1 70B Instruct",match:{equals:"meta-llama/llama-3.1-70b-instruct"},prices:{input_mtok:.1,output_mtok:.28}},{id:"meta-llama/llama-3.1-8b-instruct",match:{equals:"meta-llama/llama-3.1-8b-instruct"},prices:{input_mtok:.02,output_mtok:.03}},{id:"meta-llama/llama-3.1-8b-instruct:free",match:{equals:"meta-llama/llama-3.1-8b-instruct:free"},prices:{}},{id:"meta-llama/llama-3.2-11b-vision-instruct",name:"Llama 3.2 11B Vision Instruct",match:{equals:"meta-llama/llama-3.2-11b-vision-instruct"},prices:{input_mtok:.049,output_mtok:.049}},{id:"meta-llama/llama-3.2-11b-vision-instruct:free",match:{equals:"meta-llama/llama-3.2-11b-vision-instruct:free"},prices:{}},{id:"meta-llama/llama-3.2-1b-instruct",name:"Llama 3.2 1B Instruct",match:{equals:"meta-llama/llama-3.2-1b-instruct"},prices:{input_mtok:.005,output_mtok:.01}},{id:"meta-llama/llama-3.2-1b-instruct:free",match:{equals:"meta-llama/llama-3.2-1b-instruct:free"},prices:{}},{id:"meta-llama/llama-3.2-3b-instruct",name:"Llama 3.2 3B Instruct",match:{equals:"meta-llama/llama-3.2-3b-instruct"},prices:{input_mtok:.01,output_mtok:.02}},{id:"meta-llama/llama-3.2-3b-instruct:free",name:"Llama 3.2 3B Instruct (free)",match:{equals:"meta-llama/llama-3.2-3b-instruct:free"},prices:{}},{id:"meta-llama/llama-3.2-90b-vision-instruct",match:{equals:"meta-llama/llama-3.2-90b-vision-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"meta-llama/llama-3.3-70b-instruct",name:"Llama 3.3 70B Instruct",match:{equals:"meta-llama/llama-3.3-70b-instruct"},prices:{input_mtok:.05,output_mtok:.24}},{id:"meta-llama/llama-3.3-70b-instruct:free",name:"Llama 3.3 70B Instruct (free)",match:{equals:"meta-llama/llama-3.3-70b-instruct:free"},prices:{}},{id:"meta-llama/llama-4-maverick",name:"Llama 4 Maverick",match:{equals:"meta-llama/llama-4-maverick"},prices:{input_mtok:.15,output_mtok:.6}},{id:"meta-llama/llama-4-maverick:free",match:{equals:"meta-llama/llama-4-maverick:free"},prices:{}},{id:"meta-llama/llama-4-scout",name:"Llama 4 Scout",match:{equals:"meta-llama/llama-4-scout"},prices:{input_mtok:.08,output_mtok:.3}},{id:"meta-llama/llama-4-scout:free",match:{equals:"meta-llama/llama-4-scout:free"},prices:{}},{id:"meta-llama/llama-guard-2-8b",match:{equals:"meta-llama/llama-guard-2-8b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"meta-llama/llama-guard-3-8b",name:"Llama Guard 3 8B",match:{equals:"meta-llama/llama-guard-3-8b"},prices:{input_mtok:.02,output_mtok:.06}},{id:"meta-llama/llama-guard-4-12b",name:"Llama Guard 4 12B",match:{equals:"meta-llama/llama-guard-4-12b"},prices:{input_mtok:.05,output_mtok:.05}},{id:"microsoft/phi-3-medium-128k-instruct",match:{equals:"microsoft/phi-3-medium-128k-instruct"},prices:{input_mtok:1,output_mtok:1}},{id:"microsoft/phi-3-mini-128k-instruct",match:{equals:"microsoft/phi-3-mini-128k-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"microsoft/phi-3.5-mini-128k-instruct",match:{equals:"microsoft/phi-3.5-mini-128k-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"microsoft/phi-4",match:{equals:"microsoft/phi-4"},prices:{input_mtok:.07,output_mtok:.14}},{id:"microsoft/phi-4-mini-instruct",name:"Phi 4 Mini Instruct",match:{equals:"microsoft/phi-4-mini-instruct"},prices:{input_mtok:.08,cache_read_mtok:.08,output_mtok:.35}},{id:"microsoft/phi-4-multimodal-instruct",match:{equals:"microsoft/phi-4-multimodal-instruct"},prices:{input_mtok:.05,output_mtok:.1}},{id:"microsoft/wizardlm-2-7b",match:{equals:"microsoft/wizardlm-2-7b"},prices:{input_mtok:.07,output_mtok:.07}},{id:"microsoft/wizardlm-2-8x22b",match:{equals:"microsoft/wizardlm-2-8x22b"},prices:{input_mtok:.5,output_mtok:.5}},{id:"midnight-rose-70b",name:"Midnight Rose 70B",match:{equals:"midnight-rose-70b"},prices:{input_mtok:.8,output_mtok:.8}},{id:"minimax-m1:extended",name:"MiniMax M1 (extended)",match:{equals:"minimax-m1:extended"},prices:{input_mtok:.55,output_mtok:2.2}},{id:"minimax/minimax-01",name:"MiniMax-01",match:{equals:"minimax/minimax-01"},prices:{input_mtok:.2,output_mtok:1.1}},{id:"minimax/minimax-m1",name:"MiniMax M1",match:{equals:"minimax/minimax-m1"},prices:{input_mtok:.3,output_mtok:1.65}},{id:"minimax/minimax-m2",name:"MiniMax M2",match:{equals:"minimax/minimax-m2"},prices:{input_mtok:.255,cache_read_mtok:.03,output_mtok:1}},{id:"minimax/minimax-m2-her",name:"MiniMax M2-her",match:{or:[{equals:"minimax/minimax-m2-her"},{equals:"minimax/minimax-m2-her-20260123"}]},prices:{input_mtok:.3,cache_read_mtok:.03,output_mtok:1.2}},{id:"minimax/minimax-m2.1",name:"MiniMax M2.1",match:{equals:"minimax/minimax-m2.1"},prices:{input_mtok:.29,cache_read_mtok:.03,output_mtok:.95}},{id:"minimax/minimax-m2.5",name:"MiniMax M2.5",match:{or:[{equals:"minimax/minimax-m2.5"},{equals:"minimax/minimax-m2.5-20260211"}]},prices:{input_mtok:.15,cache_read_mtok:.05,output_mtok:.9}},{id:"minimax/minimax-m2.7",name:"MiniMax M2.7",match:{or:[{equals:"minimax/minimax-m2.7"},{equals:"minimax/minimax-m2.7-20260318"}]},prices:{input_mtok:.27,cache_read_mtok:.054,output_mtok:1.08}},{id:"minimax/minimax-m3",name:"MiniMax M3",match:{or:[{equals:"minimax/minimax-m3"},{equals:"minimax/minimax-m3-20260531"}]},prices:{input_mtok:.3,cache_read_mtok:.06,output_mtok:1.2}},{id:"ministral-3b",name:"Ministral 3B",match:{equals:"ministral-3b"},prices:{input_mtok:.04,output_mtok:.04}},{id:"ministral-8b",name:"Ministral 8B",match:{equals:"ministral-8b"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistral-7b-instruct",name:"Mistral 7B Instruct",match:{or:[{equals:"mistral-7b-instruct"},{equals:"mistral-7b-instruct-v0.3"}]},prices:{input_mtok:.028,output_mtok:.054}},{id:"mistral-7b-instruct-v0.1",name:"Mistral 7B Instruct v0.1",match:{equals:"mistral-7b-instruct-v0.1"},prices:{input_mtok:.11,output_mtok:.19}},{id:"mistral-7b-instruct-v0.2",name:"Mistral 7B Instruct v0.2",match:{equals:"mistral-7b-instruct-v0.2"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistral-7b-instruct:free",name:"Mistral 7B Instruct (free)",match:{equals:"mistral-7b-instruct:free"},prices:{}},{id:"mistral-medium",name:"Mistral Medium",match:{equals:"mistral-medium"},prices:{input_mtok:2.75,output_mtok:8.1}},{id:"mistral-nemo:free",name:"Mistral Nemo (free)",match:{equals:"mistral-nemo:free"},prices:{}},{id:"mistral-small",name:"Mistral Small",match:{equals:"mistral-small"},prices:{input_mtok:.2,output_mtok:.6}},{id:"mistral-small-24b-instruct-2501:free",name:"Mistral Small 3 (free)",match:{equals:"mistral-small-24b-instruct-2501:free"},prices:{}},{id:"mistral-small-3.1-24b-instruct:free",name:"Mistral Small 3.1 24B (free)",match:{equals:"mistral-small-3.1-24b-instruct:free"},prices:{}},{id:"mistral-small-3.2-24b-instruct:free",name:"Mistral Small 3.2 24B (free)",match:{equals:"mistral-small-3.2-24b-instruct:free"},prices:{}},{id:"mistral-tiny",name:"Mistral Tiny",match:{equals:"mistral-tiny"},prices:{input_mtok:.25,output_mtok:.25}},{id:"mistral/ministral-8b",match:{equals:"mistral/ministral-8b"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistralai/codestral-2501",match:{equals:"mistralai/codestral-2501"},prices:{input_mtok:.3,output_mtok:.9}},{id:"mistralai/codestral-2508",name:"Codestral 2508",match:{equals:"mistralai/codestral-2508"},prices:{input_mtok:.3,cache_read_mtok:.03,output_mtok:.9}},{id:"mistralai/codestral-mamba",match:{equals:"mistralai/codestral-mamba"},prices:{input_mtok:.25,output_mtok:.25}},{id:"mistralai/devstral-2512",name:"Devstral 2 2512",match:{equals:"mistralai/devstral-2512"},prices:{input_mtok:.4,cache_read_mtok:.04,output_mtok:2}},{id:"mistralai/ministral-14b-2512",name:"Ministral 3 14B 2512",match:{equals:"mistralai/ministral-14b-2512"},prices:{input_mtok:.2,cache_read_mtok:.02,output_mtok:.2}},{id:"mistralai/ministral-3b",match:{equals:"mistralai/ministral-3b"},prices:{input_mtok:.04,output_mtok:.04}},{id:"mistralai/ministral-3b-2512",name:"Ministral 3 3B 2512",match:{equals:"mistralai/ministral-3b-2512"},prices:{input_mtok:.1,cache_read_mtok:.01,output_mtok:.1}},{id:"mistralai/ministral-8b",match:{equals:"mistralai/ministral-8b"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistralai/ministral-8b-2512",name:"Ministral 3 8B 2512",match:{equals:"mistralai/ministral-8b-2512"},prices:{input_mtok:.15,cache_read_mtok:.015,output_mtok:.15}},{id:"mistralai/mistral-7b-instruct",match:{or:[{equals:"mistralai/mistral-7b-instruct"},{equals:"mistralai/mistral-7b-instruct-v0.3"}]},prices:{input_mtok:.029,output_mtok:.059}},{id:"mistralai/mistral-7b-instruct-v0.1",match:{equals:"mistralai/mistral-7b-instruct-v0.1"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistralai/mistral-7b-instruct-v0.2",match:{equals:"mistralai/mistral-7b-instruct-v0.2"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistralai/mistral-7b-instruct:free",match:{equals:"mistralai/mistral-7b-instruct:free"},prices:{}},{id:"mistralai/mistral-large",name:"Mistral Large",match:{or:[{equals:"mistralai/mistral-large"},{equals:"mistralai/mistral-large-2407"},{equals:"mistral-large-2411"}]},prices:{input_mtok:2,output_mtok:6}},{id:"mistralai/mistral-large-2512",name:"Mistral Large 3 2512",match:{equals:"mistralai/mistral-large-2512"},prices:{input_mtok:.5,cache_read_mtok:.05,output_mtok:1.5}},{id:"mistralai/mistral-medium",match:{equals:"mistralai/mistral-medium"},prices:{input_mtok:2.75,output_mtok:8.1}},{id:"mistralai/mistral-medium-3",name:"Mistral Medium 3",match:{equals:"mistralai/mistral-medium-3"},prices:{input_mtok:.4,output_mtok:2}},{id:"mistralai/mistral-medium-3-5",name:"Mistral Medium 3.5",match:{equals:"mistralai/mistral-medium-3-5"},prices:{input_mtok:1.5,output_mtok:7.5}},{id:"mistralai/mistral-medium-3.1",name:"Mistral Medium 3.1",match:{equals:"mistralai/mistral-medium-3.1"},prices:{input_mtok:.4,cache_read_mtok:.04,output_mtok:2}},{id:"mistralai/mistral-nemo",name:"Mistral Nemo",match:{equals:"mistralai/mistral-nemo"},prices:{input_mtok:.01,output_mtok:.019}},{id:"mistralai/mistral-nemo:free",match:{equals:"mistralai/mistral-nemo:free"},prices:{}},{id:"mistralai/mistral-saba",name:"Saba",match:{equals:"mistralai/mistral-saba"},prices:{input_mtok:.2,output_mtok:.6}},{id:"mistralai/mistral-small",match:{equals:"mistralai/mistral-small"},prices:{input_mtok:.2,output_mtok:.6}},{id:"mistralai/mistral-small-24b-instruct-2501",name:"Mistral Small 3",match:{equals:"mistralai/mistral-small-24b-instruct-2501"},prices:{input_mtok:.05,output_mtok:.09}},{id:"mistralai/mistral-small-24b-instruct-2501:free",match:{equals:"mistralai/mistral-small-24b-instruct-2501:free"},prices:{}},{id:"mistralai/mistral-small-2603",name:"Mistral Small 4",match:{equals:"mistralai/mistral-small-2603"},prices:{input_mtok:.15,cache_read_mtok:.015,output_mtok:.6}},{id:"mistralai/mistral-small-3.1-24b-instruct",name:"Mistral Small 3.1 24B",match:{equals:"mistralai/mistral-small-3.1-24b-instruct"},prices:{input_mtok:.05,output_mtok:.15}},{id:"mistralai/mistral-small-3.1-24b-instruct:free",match:{equals:"mistralai/mistral-small-3.1-24b-instruct:free"},prices:{}},{id:"mistralai/mistral-small-3.2-24b-instruct",name:"Mistral Small 3.2 24B",match:{equals:"mistralai/mistral-small-3.2-24b-instruct"},prices:{input_mtok:.075,output_mtok:.2}},{id:"mistralai/mistral-tiny",match:{equals:"mistralai/mistral-tiny"},prices:{input_mtok:.25,output_mtok:.25}},{id:"mistralai/mixtral-8x22b-instruct",match:{equals:"mistralai/mixtral-8x22b-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"mistralai/mixtral-8x7b-instruct",match:{equals:"mistralai/mixtral-8x7b-instruct"},prices:{input_mtok:.24,output_mtok:.24}},{id:"mistralai/pixtral-12b",match:{equals:"mistralai/pixtral-12b"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistralai/pixtral-large-2411",match:{equals:"mistralai/pixtral-large-2411"},prices:{input_mtok:2,output_mtok:6}},{id:"mistralai/voxtral-small-24b-2507",name:"Voxtral Small 24B 2507",match:{equals:"mistralai/voxtral-small-24b-2507"},prices:{input_mtok:.1,cache_read_mtok:.01,output_mtok:.3}},{id:"mixtral-8x7b-instruct",name:"Mixtral 8x7B Instruct",match:{equals:"mixtral-8x7b-instruct"},prices:{input_mtok:.08,output_mtok:.24}},{id:"mn-celeste-12b",name:"Mistral Nemo 12B Celeste",match:{equals:"mn-celeste-12b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"mn-inferor-12b",name:"Mistral Nemo Inferor 12B",match:{equals:"mn-inferor-12b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"mn-starcannon-12b",name:"Starcannon 12B",match:{equals:"mn-starcannon-12b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"moonshotai/kimi-k2",name:"Kimi K2 0711",match:{equals:"moonshotai/kimi-k2"},prices:{input_mtok:.57,output_mtok:2.3}},{id:"moonshotai/kimi-k2-0905",name:"Kimi K2 0905",match:{equals:"moonshotai/kimi-k2-0905"},prices:{input_mtok:.6,output_mtok:2.5}},{id:"moonshotai/kimi-k2-thinking",name:"Kimi K2 Thinking",match:{equals:"moonshotai/kimi-k2-thinking"},prices:{input_mtok:.6,output_mtok:2.5}},{id:"moonshotai/kimi-k2.5",name:"Kimi K2.5",match:{equals:"moonshotai/kimi-k2.5"},prices:{input_mtok:.4,cache_read_mtok:.09,output_mtok:1.9}},{id:"moonshotai/kimi-k2.6",name:"Kimi K2.6",match:{equals:"moonshotai/kimi-k2.6"},prices:{input_mtok:.68,cache_read_mtok:.34,output_mtok:3.41}},{id:"moonshotai/kimi-k2.6:free",name:"Kimi K2.6 (free)",match:{equals:"moonshotai/kimi-k2.6:free"},prices:{}},{id:"moonshotai/kimi-k2.7-code",name:"Kimi K2.7 Code",match:{or:[{equals:"moonshotai/kimi-k2.7-code"},{equals:"moonshotai/kimi-k2.7-code-20260612"}]},context_window:262144,price_comments:"Ref: https://openrouter.ai/api/v1/models",prices:{input_mtok:.75,cache_read_mtok:.16,output_mtok:3.5}},{id:"moonshotai/kimi-vl-a3b-thinking:free",match:{equals:"moonshotai/kimi-vl-a3b-thinking:free"},prices:{}},{id:"moonshotai/moonlight-16b-a3b-instruct:free",match:{equals:"moonshotai/moonlight-16b-a3b-instruct:free"},prices:{}},{id:"morph/morph-v3-fast",name:"Morph V3 Fast",match:{equals:"morph/morph-v3-fast"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"morph/morph-v3-large",name:"Morph V3 Large",match:{equals:"morph/morph-v3-large"},prices:{input_mtok:.9,output_mtok:1.9}},{id:"mythalion-13b",name:"Mythalion 13B",match:{equals:"mythalion-13b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"neversleep/llama-3-lumimaid-70b",match:{equals:"neversleep/llama-3-lumimaid-70b"},prices:{input_mtok:3.375,output_mtok:4.5}},{id:"neversleep/llama-3-lumimaid-8b",match:{or:[{equals:"neversleep/llama-3-lumimaid-8b"},{equals:"neversleep/llama-3-lumimaid-8b:extended"}]},prices:{input_mtok:.09375,output_mtok:.75}},{id:"neversleep/llama-3.1-lumimaid-70b",match:{equals:"neversleep/llama-3.1-lumimaid-70b"},prices:{input_mtok:1.5,output_mtok:2.25}},{id:"neversleep/llama-3.1-lumimaid-8b",match:{equals:"neversleep/llama-3.1-lumimaid-8b"},prices:{input_mtok:.09375,output_mtok:.75}},{id:"neversleep/noromaid-20b",match:{equals:"neversleep/noromaid-20b"},prices:{input_mtok:.75,output_mtok:1.5}},{id:"nex-agi/nex-n2-pro:free",name:"Nex-N2-Pro (free)",match:{equals:"nex-agi/nex-n2-pro:free"},prices:{}},{id:"noromaid-20b",name:"Noromaid 20B",match:{equals:"noromaid-20b"},prices:{input_mtok:1.25,output_mtok:2}},{id:"nothingiisreal/mn-celeste-12b",match:{equals:"nothingiisreal/mn-celeste-12b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"nous-hermes-2-mixtral-8x7b-dpo",name:"Hermes 2 Mixtral 8x7B DPO",match:{equals:"nous-hermes-2-mixtral-8x7b-dpo"},prices:{input_mtok:.6,output_mtok:.6}},{id:"nousresearch/deephermes-3-llama-3-8b-preview:free",match:{equals:"nousresearch/deephermes-3-llama-3-8b-preview:free"},prices:{}},{id:"nousresearch/hermes-2-pro-llama-3-8b",match:{equals:"nousresearch/hermes-2-pro-llama-3-8b"},prices:{input_mtok:.025,output_mtok:.04}},{id:"nousresearch/hermes-3-llama-3.1-405b",name:"Hermes 3 405B Instruct",match:{equals:"nousresearch/hermes-3-llama-3.1-405b"},prices:{input_mtok:.7,output_mtok:.8}},{id:"nousresearch/hermes-3-llama-3.1-405b:free",name:"Hermes 3 405B Instruct (free)",match:{equals:"nousresearch/hermes-3-llama-3.1-405b:free"},prices:{}},{id:"nousresearch/hermes-3-llama-3.1-70b",name:"Hermes 3 70B Instruct",match:{equals:"nousresearch/hermes-3-llama-3.1-70b"},prices:{input_mtok:.12,output_mtok:.3}},{id:"nousresearch/hermes-4-405b",name:"Hermes 4 405B",match:{equals:"nousresearch/hermes-4-405b"},prices:{input_mtok:1,output_mtok:3}},{id:"nousresearch/hermes-4-70b",name:"Hermes 4 70B",match:{equals:"nousresearch/hermes-4-70b"},prices:{input_mtok:.13,output_mtok:.4}},{id:"nousresearch/nous-hermes-2-mixtral-8x7b-dpo",match:{equals:"nousresearch/nous-hermes-2-mixtral-8x7b-dpo"},prices:{input_mtok:.6,output_mtok:.6}},{id:"nousresearch/nous-hermes-llama2-13b",match:{equals:"nousresearch/nous-hermes-llama2-13b"},prices:{input_mtok:.18,output_mtok:.18}},{id:"nvidia/llama-3.1-nemotron-70b-instruct",match:{equals:"nvidia/llama-3.1-nemotron-70b-instruct"},prices:{input_mtok:.12,output_mtok:.3}},{id:"nvidia/llama-3.1-nemotron-70b-instruct:free",match:{equals:"nvidia/llama-3.1-nemotron-70b-instruct:free"},prices:{}},{id:"nvidia/llama-3.1-nemotron-nano-8b-v1:free",match:{equals:"nvidia/llama-3.1-nemotron-nano-8b-v1:free"},prices:{}},{id:"nvidia/llama-3.1-nemotron-ultra-253b-v1:free",match:{equals:"nvidia/llama-3.1-nemotron-ultra-253b-v1:free"},prices:{}},{id:"nvidia/llama-3.3-nemotron-super-49b-v1.5",name:"Llama 3.3 Nemotron Super 49B V1.5",match:{equals:"nvidia/llama-3.3-nemotron-super-49b-v1.5"},prices:{input_mtok:.4,output_mtok:.4}},{id:"nvidia/llama-3.3-nemotron-super-49b-v1:free",match:{equals:"nvidia/llama-3.3-nemotron-super-49b-v1:free"},prices:{}},{id:"nvidia/nemotron-3-nano-30b-a3b",name:"Nemotron 3 Nano 30B A3B",match:{equals:"nvidia/nemotron-3-nano-30b-a3b"},prices:{input_mtok:.05,output_mtok:.2}},{id:"nvidia/nemotron-3-nano-30b-a3b:free",name:"Nemotron 3 Nano 30B A3B (free)",match:{equals:"nvidia/nemotron-3-nano-30b-a3b:free"},prices:{}},{id:"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",name:"Nemotron 3 Nano Omni (free)",match:{equals:"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free"},prices:{}},{id:"nvidia/nemotron-3-super-120b-a12b",name:"Nemotron 3 Super",match:{equals:"nvidia/nemotron-3-super-120b-a12b"},prices:{input_mtok:.09,output_mtok:.45}},{id:"nvidia/nemotron-3-super-120b-a12b:free",name:"Nemotron 3 Super (free)",match:{equals:"nvidia/nemotron-3-super-120b-a12b:free"},prices:{}},{id:"nvidia/nemotron-3-ultra-550b-a55b",name:"Nemotron 3 Ultra",match:{equals:"nvidia/nemotron-3-ultra-550b-a55b"},prices:{input_mtok:.5,cache_read_mtok:.15,output_mtok:2.5}},{id:"nvidia/nemotron-3-ultra-550b-a55b:free",name:"Nemotron 3 Ultra (free)",match:{equals:"nvidia/nemotron-3-ultra-550b-a55b:free"},prices:{}},{id:"nvidia/nemotron-3.5-content-safety:free",name:"Nemotron 3.5 Content Safety (free)",match:{equals:"nvidia/nemotron-3.5-content-safety:free"},prices:{}},{id:"nvidia/nemotron-nano-12b-v2-vl:free",name:"Nemotron Nano 12B 2 VL (free)",match:{equals:"nvidia/nemotron-nano-12b-v2-vl:free"},prices:{}},{id:"nvidia/nemotron-nano-9b-v2",name:"Nemotron Nano 9B V2",match:{equals:"nvidia/nemotron-nano-9b-v2"},prices:{input_mtok:.04,output_mtok:.16}},{id:"nvidia/nemotron-nano-9b-v2:free",name:"Nemotron Nano 9B V2 (free)",match:{equals:"nvidia/nemotron-nano-9b-v2:free"},prices:{}},{id:"o1-mini",name:"o1-mini",match:{or:[{equals:"o1-mini"},{equals:"o1-mini-2024-09-12"}]},prices:{input_mtok:1.1,cache_read_mtok:.55,output_mtok:4.4}},{id:"open-r1/olympiccoder-32b:free",match:{equals:"open-r1/olympiccoder-32b:free"},prices:{}},{id:"open-r1/olympiccoder-7b:free",match:{equals:"open-r1/olympiccoder-7b:free"},prices:{}},{id:"openai/chatgpt-4o-latest",match:{equals:"openai/chatgpt-4o-latest"},prices:{input_mtok:5,output_mtok:15}},{id:"openai/codex-mini",match:{equals:"openai/codex-mini"},prices:{input_mtok:1.5,cache_read_mtok:.375,output_mtok:6}},{id:"openai/gpt-3.5-turbo",name:"GPT-3.5 Turbo",match:{or:[{equals:"openai/gpt-3.5-turbo"},{equals:"gpt-3.5-turbo-0125"}]},prices:{input_mtok:.5,output_mtok:1.5}},{id:"openai/gpt-3.5-turbo-0613",name:"GPT-3.5 Turbo (older v0613)",match:{equals:"openai/gpt-3.5-turbo-0613"},prices:{input_mtok:1,output_mtok:2}},{id:"openai/gpt-3.5-turbo-1106",match:{equals:"openai/gpt-3.5-turbo-1106"},prices:{input_mtok:1,output_mtok:2}},{id:"openai/gpt-3.5-turbo-16k",name:"GPT-3.5 Turbo 16k",match:{equals:"openai/gpt-3.5-turbo-16k"},prices:{input_mtok:3,output_mtok:4}},{id:"openai/gpt-3.5-turbo-instruct",name:"GPT-3.5 Turbo Instruct",match:{equals:"openai/gpt-3.5-turbo-instruct"},prices:{input_mtok:1.5,output_mtok:2}},{id:"openai/gpt-4",name:"GPT-4",match:{or:[{equals:"openai/gpt-4"},{equals:"gpt-4-0314"}]},prices:{input_mtok:30,output_mtok:60}},{id:"openai/gpt-4-1106-preview",match:{equals:"openai/gpt-4-1106-preview"},prices:{input_mtok:10,output_mtok:30}},{id:"openai/gpt-4-32k",match:{or:[{equals:"openai/gpt-4-32k"},{equals:"openai/gpt-4-32k-0314"}]},prices:{input_mtok:60,output_mtok:120}},{id:"openai/gpt-4-turbo",name:"GPT-4 Turbo",match:{or:[{equals:"openai/gpt-4-turbo"},{equals:"openai/gpt-4-turbo-preview"}]},prices:{input_mtok:10,output_mtok:30}},{id:"openai/gpt-4.1",name:"GPT-4.1",match:{equals:"openai/gpt-4.1"},prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}},{id:"openai/gpt-4.1-mini",name:"GPT-4.1 Mini",match:{equals:"openai/gpt-4.1-mini"},prices:{input_mtok:.4,cache_read_mtok:.1,output_mtok:1.6}},{id:"openai/gpt-4.1-nano",name:"GPT-4.1 Nano",match:{equals:"openai/gpt-4.1-nano"},prices:{input_mtok:.1,cache_read_mtok:.025,output_mtok:.4}},{id:"openai/gpt-4.5-preview",match:{equals:"openai/gpt-4.5-preview"},prices:{input_mtok:75,output_mtok:150}},{id:"openai/gpt-4o",match:{or:[{equals:"openai/gpt-4o"},{equals:"openai/gpt-4o-2024-08-06"},{equals:"openai/gpt-4o-2024-11-20"},{equals:"openai/gpt-4o-audio-preview"}]},prices:{input_mtok:2.5,output_mtok:10}},{id:"openai/gpt-4o-2024-05-13",name:"GPT-4o (2024-05-13)",match:{equals:"openai/gpt-4o-2024-05-13"},prices:{input_mtok:5,output_mtok:15}},{id:"openai/gpt-4o-mini",name:"GPT-4o-mini",match:{or:[{equals:"openai/gpt-4o-mini"},{equals:"openai/gpt-4o-mini-2024-07-18"}]},prices:{input_mtok:.15,cache_read_mtok:.075,output_mtok:.6}},{id:"openai/gpt-4o-mini-search-preview",name:"GPT-4o-mini Search Preview",match:{equals:"openai/gpt-4o-mini-search-preview"},prices:{input_mtok:.15,output_mtok:.6}},{id:"openai/gpt-4o-search-preview",name:"GPT-4o Search Preview",match:{equals:"openai/gpt-4o-search-preview"},prices:{input_mtok:2.5,output_mtok:10}},{id:"openai/gpt-4o:extended",match:{equals:"openai/gpt-4o:extended"},prices:{input_mtok:6,output_mtok:18}},{id:"openai/gpt-5",name:"GPT-5",match:{or:[{equals:"openai/gpt-5"},{equals:"openai/gpt-5-chat"},{equals:"openai/gpt-5-codex"},{equals:"openai/gpt-5.1-codex-max"}]},prices:{input_mtok:1.25,cache_read_mtok:.125,output_mtok:10}},{id:"openai/gpt-5-image",name:"GPT-5 Image",match:{equals:"openai/gpt-5-image"},prices:{input_mtok:10,cache_read_mtok:1.25,output_mtok:10}},{id:"openai/gpt-5-image-mini",name:"GPT-5 Image Mini",match:{equals:"openai/gpt-5-image-mini"},prices:{input_mtok:2.5,cache_read_mtok:.25,output_mtok:2}},{id:"openai/gpt-5-mini",name:"GPT-5 Mini",match:{equals:"openai/gpt-5-mini"},prices:{input_mtok:.25,cache_read_mtok:.025,output_mtok:2}},{id:"openai/gpt-5-nano",name:"GPT-5 Nano",match:{equals:"openai/gpt-5-nano"},prices:{input_mtok:.05,cache_read_mtok:.01,output_mtok:.4}},{id:"openai/gpt-5-pro",name:"GPT-5 Pro",match:{equals:"openai/gpt-5-pro"},prices:{input_mtok:15,output_mtok:120}},{id:"openai/gpt-5.1",name:"GPT-5.1",match:{or:[{equals:"openai/gpt-5.1"},{equals:"openai/gpt-5.1-chat"},{equals:"openai/gpt-5.1-codex"}]},prices:{input_mtok:1.25,cache_read_mtok:.13,output_mtok:10}},{id:"openai/gpt-5.1-codex-mini",name:"GPT-5.1-Codex-Mini",match:{equals:"openai/gpt-5.1-codex-mini"},prices:{input_mtok:.25,cache_read_mtok:.025,output_mtok:2}},{id:"openai/gpt-5.2",name:"GPT-5.2",match:{or:[{equals:"openai/gpt-5.2"},{equals:"openai/gpt-5.2-chat"},{equals:"openai/gpt-5.2-codex"}]},prices:{input_mtok:1.75,cache_read_mtok:.175,output_mtok:14}},{id:"openai/gpt-5.2-pro",name:"GPT-5.2 Pro",match:{equals:"openai/gpt-5.2-pro"},prices:{input_mtok:21,output_mtok:168}},{id:"openai/gpt-5.3-chat",name:"GPT-5.3 Chat",match:{equals:"openai/gpt-5.3-chat"},prices:{input_mtok:1.75,cache_read_mtok:.175,output_mtok:14}},{id:"openai/gpt-5.3-codex",name:"GPT-5.3-Codex",match:{equals:"openai/gpt-5.3-codex"},prices:{input_mtok:1.75,cache_read_mtok:.175,output_mtok:14}},{id:"openai/gpt-5.4",name:"GPT-5.4",match:{equals:"openai/gpt-5.4"},prices:{input_mtok:2.5,cache_read_mtok:.25,output_mtok:15}},{id:"openai/gpt-5.4-image-2",name:"GPT-5.4 Image 2",match:{equals:"openai/gpt-5.4-image-2"},prices:{input_mtok:8,cache_read_mtok:2,output_mtok:15}},{id:"openai/gpt-5.4-mini",name:"GPT-5.4 Mini",match:{equals:"openai/gpt-5.4-mini"},prices:{input_mtok:.75,cache_read_mtok:.075,output_mtok:4.5}},{id:"openai/gpt-5.4-nano",name:"GPT-5.4 Nano",match:{equals:"openai/gpt-5.4-nano"},prices:{input_mtok:.2,cache_read_mtok:.02,output_mtok:1.25}},{id:"openai/gpt-5.4-pro",name:"GPT-5.4 Pro",match:{equals:"openai/gpt-5.4-pro"},prices:{input_mtok:30,output_mtok:180}},{id:"openai/gpt-5.5",name:"GPT-5.5",match:{equals:"openai/gpt-5.5"},prices:{input_mtok:5,cache_read_mtok:.5,output_mtok:30}},{id:"openai/gpt-5.5-pro",name:"GPT-5.5 Pro",match:{equals:"openai/gpt-5.5-pro"},prices:{input_mtok:30,output_mtok:180}},{id:"openai/gpt-audio",name:"GPT Audio",match:{equals:"openai/gpt-audio"},prices:{input_mtok:2.5,output_mtok:10}},{id:"openai/gpt-audio-mini",name:"GPT Audio Mini",match:{equals:"openai/gpt-audio-mini"},prices:{input_mtok:.6,output_mtok:2.4}},{id:"openai/gpt-chat-latest",name:"GPT Chat Latest",match:{equals:"openai/gpt-chat-latest"},prices:{input_mtok:5,cache_read_mtok:.5,output_mtok:30}},{id:"openai/gpt-oss-120b",name:"gpt-oss-120b",match:{equals:"openai/gpt-oss-120b"},prices:{input_mtok:.039,output_mtok:.18}},{id:"openai/gpt-oss-120b:free",name:"gpt-oss-120b (free)",match:{equals:"openai/gpt-oss-120b:free"},prices:{}},{id:"openai/gpt-oss-20b",name:"gpt-oss-20b",match:{equals:"openai/gpt-oss-20b"},prices:{input_mtok:.029,output_mtok:.14}},{id:"openai/gpt-oss-20b:free",name:"gpt-oss-20b (free)",match:{equals:"openai/gpt-oss-20b:free"},prices:{}},{id:"openai/gpt-oss-safeguard-20b",name:"gpt-oss-safeguard-20b",match:{equals:"openai/gpt-oss-safeguard-20b"},prices:{input_mtok:.075,cache_read_mtok:.037,output_mtok:.3}},{id:"openai/o1",name:"o1",match:{or:[{equals:"openai/o1"},{equals:"o1-preview"},{equals:"o1-preview-2024-09-12"}]},prices:{input_mtok:15,cache_read_mtok:7.5,output_mtok:60}},{id:"openai/o1-mini",match:{or:[{equals:"openai/o1-mini"},{equals:"openai/o1-mini-2024-09-12"}]},prices:{input_mtok:1.1,output_mtok:4.4}},{id:"openai/o1-pro",name:"o1-pro",match:{equals:"openai/o1-pro"},prices:{input_mtok:150,output_mtok:600}},{id:"openai/o3",name:"o3",match:{equals:"openai/o3"},prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}},{id:"openai/o3-deep-research",name:"o3 Deep Research",match:{equals:"openai/o3-deep-research"},prices:{input_mtok:10,cache_read_mtok:2.5,output_mtok:40}},{id:"openai/o3-mini",name:"o3 Mini",match:{or:[{equals:"openai/o3-mini"},{equals:"openai/o3-mini-high"}]},prices:{input_mtok:1.1,cache_read_mtok:.55,output_mtok:4.4}},{id:"openai/o3-pro",name:"o3 Pro",match:{equals:"openai/o3-pro"},prices:{input_mtok:20,output_mtok:80}},{id:"openai/o4-mini",name:"o4 Mini",match:{or:[{equals:"openai/o4-mini"},{equals:"openai/o4-mini-high"}]},prices:{input_mtok:1.1,cache_read_mtok:.275,output_mtok:4.4}},{id:"openai/o4-mini-deep-research",name:"o4 Mini Deep Research",match:{equals:"openai/o4-mini-deep-research"},prices:{input_mtok:2,cache_read_mtok:.5,output_mtok:8}},{id:"openchat/openchat-7b",match:{equals:"openchat/openchat-7b"},prices:{input_mtok:.07,output_mtok:.07}},{id:"openhands-lm-32b-v0.1",name:"OpenHands LM 32B V0.1",match:{equals:"openhands-lm-32b-v0.1"},prices:{input_mtok:2.6,output_mtok:3.4}},{id:"perceptron/perceptron-mk1",name:"Perceptron Mk1",match:{equals:"perceptron/perceptron-mk1"},prices:{input_mtok:.15,output_mtok:1.5}},{id:"perplexity/llama-3.1-sonar-large-128k-online",match:{equals:"perplexity/llama-3.1-sonar-large-128k-online"},prices:{input_mtok:1,output_mtok:1}},{id:"perplexity/llama-3.1-sonar-small-128k-online",match:{equals:"perplexity/llama-3.1-sonar-small-128k-online"},prices:{input_mtok:.2,output_mtok:.2}},{id:"perplexity/r1-1776",match:{equals:"perplexity/r1-1776"},prices:{input_mtok:2,output_mtok:8}},{id:"perplexity/sonar",match:{equals:"perplexity/sonar"},prices:{input_mtok:1,output_mtok:1}},{id:"perplexity/sonar-deep-research",match:{equals:"perplexity/sonar-deep-research"},prices:{input_mtok:2,output_mtok:8}},{id:"perplexity/sonar-pro",match:{equals:"perplexity/sonar-pro"},prices:{input_mtok:3,output_mtok:15}},{id:"perplexity/sonar-reasoning",match:{equals:"perplexity/sonar-reasoning"},prices:{input_mtok:1,output_mtok:5}},{id:"perplexity/sonar-reasoning-pro",match:{equals:"perplexity/sonar-reasoning-pro"},prices:{input_mtok:2,output_mtok:8}},{id:"phi-3-medium-128k-instruct",name:"Phi-3 Medium 128K Instruct",match:{equals:"phi-3-medium-128k-instruct"},prices:{input_mtok:1,output_mtok:1}},{id:"phi-3-mini-128k-instruct",name:"Phi-3 Mini 128K Instruct",match:{equals:"phi-3-mini-128k-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"phi-3.5-mini-128k-instruct",name:"Phi-3.5 Mini 128K Instruct",match:{equals:"phi-3.5-mini-128k-instruct"},prices:{input_mtok:.1,output_mtok:.1}},{id:"phi-4-multimodal-instruct",name:"Phi 4 Multimodal Instruct",match:{equals:"phi-4-multimodal-instruct"},prices:{input_mtok:.05,output_mtok:.1}},{id:"phi-4-reasoning-plus",name:"Phi 4 Reasoning Plus",match:{equals:"phi-4-reasoning-plus"},prices:{input_mtok:.07,output_mtok:.35}},{id:"phi-4-reasoning-plus:free",name:"Phi 4 Reasoning Plus (free)",match:{equals:"phi-4-reasoning-plus:free"},prices:{}},{id:"phi-4-reasoning:free",name:"Phi 4 Reasoning (free)",match:{equals:"phi-4-reasoning:free"},prices:{}},{id:"pixtral-12b",name:"Pixtral 12B",match:{equals:"pixtral-12b"},prices:{input_mtok:.1,output_mtok:.1}},{id:"pixtral-large-2411",name:"Pixtral Large 2411",match:{equals:"pixtral-large-2411"},prices:{input_mtok:2,output_mtok:6}},{id:"poolside/laguna-m.1:free",name:"Laguna M.1 (free)",match:{equals:"poolside/laguna-m.1:free"},prices:{}},{id:"poolside/laguna-xs.2:free",name:"Laguna XS.2 (free)",match:{equals:"poolside/laguna-xs.2:free"},prices:{}},{id:"prime-intellect/intellect-3",name:"INTELLECT-3",match:{equals:"prime-intellect/intellect-3"},prices:{input_mtok:.2,output_mtok:1.1}},{id:"pygmalionai/mythalion-13b",match:{equals:"pygmalionai/mythalion-13b"},prices:{input_mtok:.5625,output_mtok:1.125}},{id:"qwen-2-72b-instruct",name:"Qwen 2 72B Instruct",match:{equals:"qwen-2-72b-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"qwen-2.5-72b-instruct:free",name:"Qwen2.5 72B Instruct (free)",match:{equals:"qwen-2.5-72b-instruct:free"},prices:{}},{id:"qwen-2.5-coder-32b-instruct:free",name:"Qwen2.5 Coder 32B Instruct (free)",match:{equals:"qwen-2.5-coder-32b-instruct:free"},prices:{}},{id:"qwen-2.5-vl-7b-instruct",name:"Qwen2.5-VL 7B Instruct",match:{equals:"qwen-2.5-vl-7b-instruct"},prices:{input_mtok:.2,output_mtok:.2}},{id:"qwen-max",name:"Qwen-Max",match:{equals:"qwen-max"},prices:{input_mtok:1.6,cache_read_mtok:.64,output_mtok:6.4}},{id:"qwen-turbo",name:"Qwen-Turbo",match:{equals:"qwen-turbo"},prices:{input_mtok:.05,cache_read_mtok:.02,output_mtok:.2}},{id:"qwen-vl-max",name:"Qwen VL Max",match:{equals:"qwen-vl-max"},prices:{input_mtok:.8,output_mtok:3.2}},{id:"qwen-vl-plus",name:"Qwen VL Plus",match:{equals:"qwen-vl-plus"},prices:{input_mtok:.21,output_mtok:.63}},{id:"qwen/qwen-2-72b-instruct",match:{equals:"qwen/qwen-2-72b-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"qwen/qwen-2.5-72b-instruct",name:"Qwen2.5 72B Instruct",match:{equals:"qwen/qwen-2.5-72b-instruct"},prices:{input_mtok:.12,output_mtok:.39}},{id:"qwen/qwen-2.5-72b-instruct:free",match:{equals:"qwen/qwen-2.5-72b-instruct:free"},prices:{}},{id:"qwen/qwen-2.5-7b-instruct",name:"Qwen2.5 7B Instruct",match:{equals:"qwen/qwen-2.5-7b-instruct"},prices:{input_mtok:.04,output_mtok:.1}},{id:"qwen/qwen-2.5-7b-instruct:free",match:{equals:"qwen/qwen-2.5-7b-instruct:free"},prices:{}},{id:"qwen/qwen-2.5-coder-32b-instruct",name:"Qwen2.5 Coder 32B Instruct",match:{equals:"qwen/qwen-2.5-coder-32b-instruct"},prices:{input_mtok:.06,output_mtok:.15}},{id:"qwen/qwen-2.5-coder-32b-instruct:free",match:{equals:"qwen/qwen-2.5-coder-32b-instruct:free"},prices:{}},{id:"qwen/qwen-2.5-vl-72b-instruct",match:{equals:"qwen/qwen-2.5-vl-72b-instruct"},prices:{input_mtok:.6,output_mtok:.6}},{id:"qwen/qwen-2.5-vl-7b-instruct",match:{equals:"qwen/qwen-2.5-vl-7b-instruct"},prices:{input_mtok:.2,output_mtok:.2}},{id:"qwen/qwen-2.5-vl-7b-instruct:free",match:{equals:"qwen/qwen-2.5-vl-7b-instruct:free"},prices:{}},{id:"qwen/qwen-max",match:{equals:"qwen/qwen-max"},prices:{input_mtok:1.6,output_mtok:6.4}},{id:"qwen/qwen-plus",name:"Qwen-Plus",match:{equals:"qwen/qwen-plus"},prices:{input_mtok:.4,cache_read_mtok:.16,output_mtok:1.2}},{id:"qwen/qwen-plus-2025-07-28",name:"Qwen Plus 0728",match:{equals:"qwen/qwen-plus-2025-07-28"},prices:{input_mtok:.26,output_mtok:.78}},{id:"qwen/qwen-plus-2025-07-28:thinking",name:"Qwen Plus 0728 (thinking)",match:{equals:"qwen/qwen-plus-2025-07-28:thinking"},prices:{input_mtok:.26,cache_write_mtok:.325,output_mtok:.78}},{id:"qwen/qwen-turbo",match:{equals:"qwen/qwen-turbo"},prices:{input_mtok:.05,output_mtok:.2}},{id:"qwen/qwen-vl-max",match:{equals:"qwen/qwen-vl-max"},prices:{input_mtok:.8,output_mtok:3.2}},{id:"qwen/qwen-vl-plus",match:{equals:"qwen/qwen-vl-plus"},prices:{input_mtok:.21,output_mtok:.63}},{id:"qwen/qwen2.5-coder-7b-instruct",match:{equals:"qwen/qwen2.5-coder-7b-instruct"},prices:{input_mtok:.2,output_mtok:.2}},{id:"qwen/qwen2.5-vl-32b-instruct",match:{equals:"qwen/qwen2.5-vl-32b-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"qwen/qwen2.5-vl-32b-instruct:free",match:{equals:"qwen/qwen2.5-vl-32b-instruct:free"},prices:{}},{id:"qwen/qwen2.5-vl-3b-instruct:free",match:{equals:"qwen/qwen2.5-vl-3b-instruct:free"},prices:{}},{id:"qwen/qwen2.5-vl-72b-instruct",match:{equals:"qwen/qwen2.5-vl-72b-instruct"},prices:{input_mtok:.7,output_mtok:.7}},{id:"qwen/qwen2.5-vl-72b-instruct:free",match:{equals:"qwen/qwen2.5-vl-72b-instruct:free"},prices:{}},{id:"qwen/qwen3-14b",name:"Qwen3 14B",match:{equals:"qwen/qwen3-14b"},prices:{input_mtok:.06,output_mtok:.24}},{id:"qwen/qwen3-235b-a22b",name:"Qwen3 235B A22B",match:{equals:"qwen/qwen3-235b-a22b"},prices:{input_mtok:.13,output_mtok:.6}},{id:"qwen/qwen3-235b-a22b-2507",name:"Qwen3 235B A22B Instruct 2507",match:{equals:"qwen/qwen3-235b-a22b-2507"},prices:{input_mtok:.09,output_mtok:.1}},{id:"qwen/qwen3-235b-a22b-thinking-2507",name:"Qwen3 235B A22B Thinking 2507",match:{equals:"qwen/qwen3-235b-a22b-thinking-2507"},prices:{input_mtok:.1,cache_read_mtok:.1,output_mtok:.1}},{id:"qwen/qwen3-30b-a3b",name:"Qwen3 30B A3B",match:{equals:"qwen/qwen3-30b-a3b"},prices:{input_mtok:.08,output_mtok:.29}},{id:"qwen/qwen3-30b-a3b-instruct-2507",name:"Qwen3 30B A3B Instruct 2507",match:{equals:"qwen/qwen3-30b-a3b-instruct-2507"},prices:{input_mtok:.04815,output_mtok:.19305}},{id:"qwen/qwen3-30b-a3b-thinking-2507",name:"Qwen3 30B A3B Thinking 2507",match:{equals:"qwen/qwen3-30b-a3b-thinking-2507"},prices:{input_mtok:.08,cache_read_mtok:.08,output_mtok:.4}},{id:"qwen/qwen3-32b",name:"Qwen3 32B",match:{equals:"qwen/qwen3-32b"},prices:{input_mtok:.1,output_mtok:.3}},{id:"qwen/qwen3-8b",name:"Qwen3 8B",match:{equals:"qwen/qwen3-8b"},prices:{input_mtok:.035,output_mtok:.138}},{id:"qwen/qwen3-coder",name:"Qwen3 Coder 480B A35B",match:{or:[{equals:"qwen/qwen3-coder"},{equals:"qwen/qwen3-coder-480b-a35b-07-25"}]},prices:{input_mtok:.22,output_mtok:1.8}},{id:"qwen/qwen3-coder-30b-a3b-instruct",name:"Qwen3 Coder 30B A3B Instruct",match:{equals:"qwen/qwen3-coder-30b-a3b-instruct"},prices:{input_mtok:.07,output_mtok:.27}},{id:"qwen/qwen3-coder-flash",name:"Qwen3 Coder Flash",match:{equals:"qwen/qwen3-coder-flash"},prices:{input_mtok:.195,cache_write_mtok:.24375,cache_read_mtok:.039,output_mtok:.975}},{id:"qwen/qwen3-coder-next",name:"Qwen3 Coder Next",match:{or:[{equals:"qwen/qwen3-coder-next"},{equals:"qwen/qwen3-coder-next-2025-02-03"}]},prices:{input_mtok:.11,cache_read_mtok:.07,output_mtok:.8}},{id:"qwen/qwen3-coder-plus",name:"Qwen3 Coder Plus",match:{equals:"qwen/qwen3-coder-plus"},prices:{input_mtok:.65,cache_write_mtok:.8125,cache_read_mtok:.13,output_mtok:3.25}},{id:"qwen/qwen3-coder:free",name:"Qwen3 Coder 480B A35B (free)",match:{equals:"qwen/qwen3-coder:free"},prices:{}},{id:"qwen/qwen3-max",name:"Qwen 3 Max",match:{equals:"qwen/qwen3-max"},prices:{input_mtok:1.2,output_mtok:6}},{id:"qwen/qwen3-max-thinking",name:"Qwen3 Max Thinking",match:{or:[{equals:"qwen/qwen3-max-thinking"},{equals:"qwen/qwen3-max-thinking-20260123"}]},prices:{input_mtok:.78,output_mtok:3.9}},{id:"qwen/qwen3-next-80b-a3b-instruct",name:"Qwen3 Next 80B A3B Instruct",match:{or:[{equals:"qwen/qwen3-next-80b-a3b-instruct"},{equals:"qwen/qwen3-next-80b-a3b-instruct-2509"}]},prices:{input_mtok:.09,output_mtok:1.1}},{id:"qwen/qwen3-next-80b-a3b-instruct:free",name:"Qwen3 Next 80B A3B Instruct (free)",match:{equals:"qwen/qwen3-next-80b-a3b-instruct:free"},prices:{}},{id:"qwen/qwen3-next-80b-a3b-thinking",name:"Qwen3 Next 80B A3B Thinking",match:{or:[{equals:"qwen/qwen3-next-80b-a3b-thinking"},{equals:"qwen/qwen3-next-80b-a3b-thinking-2509"}]},prices:{input_mtok:.0975,output_mtok:.78}},{id:"qwen/qwen3-vl-235b-a22b-instruct",name:"Qwen3 VL 235B A22B Instruct",match:{equals:"qwen/qwen3-vl-235b-a22b-instruct"},prices:{input_mtok:.2,cache_read_mtok:.11,output_mtok:.88}},{id:"qwen/qwen3-vl-235b-a22b-thinking",name:"Qwen3 VL 235B A22B Thinking",match:{equals:"qwen/qwen3-vl-235b-a22b-thinking"},prices:{input_mtok:.26,output_mtok:2.6}},{id:"qwen/qwen3-vl-30b-a3b-instruct",name:"Qwen3 VL 30B A3B Instruct",match:{equals:"qwen/qwen3-vl-30b-a3b-instruct"},prices:{input_mtok:.13,output_mtok:.52}},{id:"qwen/qwen3-vl-30b-a3b-thinking",name:"Qwen3 VL 30B A3B Thinking",match:{equals:"qwen/qwen3-vl-30b-a3b-thinking"},prices:{input_mtok:.13,output_mtok:1.56}},{id:"qwen/qwen3-vl-32b-instruct",name:"Qwen3 VL 32B Instruct",match:{equals:"qwen/qwen3-vl-32b-instruct"},prices:{input_mtok:.104,output_mtok:.416}},{id:"qwen/qwen3-vl-8b-instruct",name:"Qwen3 VL 8B Instruct",match:{equals:"qwen/qwen3-vl-8b-instruct"},prices:{input_mtok:.08,output_mtok:.5}},{id:"qwen/qwen3-vl-8b-thinking",name:"Qwen3 VL 8B Thinking",match:{equals:"qwen/qwen3-vl-8b-thinking"},prices:{input_mtok:.117,output_mtok:1.365}},{id:"qwen/qwen3.5-122b-a10b",name:"Qwen3.5-122B-A10B",match:{or:[{equals:"qwen/qwen3.5-122b-a10b"},{equals:"qwen/qwen3.5-122b-a10b-20260224"}]},prices:{input_mtok:.26,output_mtok:2.08}},{id:"qwen/qwen3.5-27b",name:"Qwen3.5-27B",match:{or:[{equals:"qwen/qwen3.5-27b"},{equals:"qwen/qwen3.5-27b-20260224"}]},prices:{input_mtok:.195,output_mtok:1.56}},{id:"qwen/qwen3.5-35b-a3b",name:"Qwen3.5-35B-A3B",match:{or:[{equals:"qwen/qwen3.5-35b-a3b"},{equals:"qwen/qwen3.5-35b-a3b-20260224"}]},prices:{input_mtok:.14,cache_read_mtok:.05,output_mtok:1}},{id:"qwen/qwen3.5-397b-a17b",name:"Qwen3.5 397B A17B",match:{or:[{equals:"qwen/qwen3.5-397b-a17b"},{equals:"qwen/qwen3.5-397b-a17b-20260216"}]},prices:{input_mtok:.39,output_mtok:2.34}},{id:"qwen/qwen3.5-9b",name:"Qwen3.5-9B",match:{or:[{equals:"qwen/qwen3.5-9b"},{equals:"qwen/qwen3.5-9b-20260310"}]},prices:{input_mtok:.1,output_mtok:.15}},{id:"qwen/qwen3.5-flash-02-23",name:"Qwen3.5-Flash",match:{or:[{equals:"qwen/qwen3.5-flash-02-23"},{equals:"qwen/qwen3.5-flash-20260224"}]},prices:{input_mtok:.065,output_mtok:.26}},{id:"qwen/qwen3.5-plus-02-15",name:"Qwen3.5 plus-02-15",match:{or:[{equals:"qwen/qwen3.5-plus-02-15"},{equals:"qwen/qwen3.5-plus-20260216"}]},prices:{input_mtok:.4,output_mtok:2.4}},{id:"qwen/qwen3.5-plus-20260420",name:"Qwen3.5 Plus 2026-04-20",match:{equals:"qwen/qwen3.5-plus-20260420"},prices:{input_mtok:.3,cache_write_mtok:.375,output_mtok:1.8}},{id:"qwen/qwen3.6-27b",name:"Qwen3.6 27B",match:{or:[{equals:"qwen/qwen3.6-27b"},{equals:"qwen/qwen3.6-27b-20260422"}]},prices:{input_mtok:.289,output_mtok:2.4}},{id:"qwen/qwen3.6-35b-a3b",name:"Qwen3.6 35B A3B",match:{or:[{equals:"qwen/qwen3.6-35b-a3b"},{equals:"qwen/qwen3.6-35b-a3b-20260415"}]},prices:{input_mtok:.14,output_mtok:1}},{id:"qwen/qwen3.6-flash",name:"Qwen3.6 Flash",match:{equals:"qwen/qwen3.6-flash"},prices:{input_mtok:.1875,cache_write_mtok:.234375,output_mtok:1.125}},{id:"qwen/qwen3.6-max-preview",name:"Qwen3.6 Max Preview",match:{or:[{equals:"qwen/qwen3.6-max-preview"},{equals:"qwen/qwen3.6-max-preview-20260420"}]},prices:{input_mtok:1.04,cache_write_mtok:1.3,output_mtok:6.24}},{id:"qwen/qwen3.6-plus",name:"Qwen3.6 Plus",match:{or:[{equals:"qwen/qwen3.6-plus"},{equals:"qwen/qwen3.6-plus-04-02"}]},prices:{input_mtok:.325,cache_write_mtok:.40625,output_mtok:1.95}},{id:"qwen/qwen3.7-max",name:"Qwen3.7 Max",match:{or:[{equals:"qwen/qwen3.7-max"},{equals:"qwen/qwen3.7-max-20260520"}]},prices:{input_mtok:1.25,cache_write_mtok:1.5625,cache_read_mtok:.25,output_mtok:3.75}},{id:"qwen/qwen3.7-plus",name:"Qwen3.7 Plus",match:{or:[{equals:"qwen/qwen3.7-plus"},{equals:"qwen/qwen3.7-plus-20260602"}]},prices:{input_mtok:.4,cache_write_mtok:.5,cache_read_mtok:.08,output_mtok:1.6}},{id:"qwen/qwq-32b",match:{equals:"qwen/qwq-32b"},prices:{input_mtok:.15,output_mtok:.2}},{id:"qwen/qwq-32b-preview",match:{equals:"qwen/qwq-32b-preview"},prices:{input_mtok:.2,output_mtok:.2}},{id:"qwen/qwq-32b-preview:free",match:{equals:"qwen/qwq-32b-preview:free"},prices:{}},{id:"qwen/qwq-32b:free",match:{equals:"qwen/qwq-32b:free"},prices:{}},{id:"qwen2.5-vl-32b-instruct",name:"Qwen2.5 VL 32B Instruct",match:{equals:"qwen2.5-vl-32b-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"qwen2.5-vl-32b-instruct:free",name:"Qwen2.5 VL 32B Instruct (free)",match:{equals:"qwen2.5-vl-32b-instruct:free"},prices:{}},{id:"qwen2.5-vl-72b-instruct:free",name:"Qwen2.5 VL 72B Instruct (free)",match:{equals:"qwen2.5-vl-72b-instruct:free"},prices:{}},{id:"qwen3-14b:free",name:"Qwen3 14B (free)",match:{equals:"qwen3-14b:free"},prices:{}},{id:"qwen3-235b-a22b:free",name:"Qwen3 235B A22B (free)",match:{equals:"qwen3-235b-a22b:free"},prices:{}},{id:"qwen3-30b-a3b:free",name:"Qwen3 30B A3B (free)",match:{equals:"qwen3-30b-a3b:free"},prices:{}},{id:"qwen3-32b:free",name:"Qwen3 32B (free)",match:{equals:"qwen3-32b:free"},prices:{}},{id:"qwen3-8b:free",name:"Qwen3 8B (free)",match:{equals:"qwen3-8b:free"},prices:{}},{id:"qwerky-72b:free",name:"Qwerky 72B (free)",match:{equals:"qwerky-72b:free"},prices:{}},{id:"qwq-32b",name:"QwQ 32B",match:{equals:"qwq-32b"},prices:{input_mtok:.15,output_mtok:.2}},{id:"qwq-32b-arliai-rpr-v1:free",name:"QwQ 32B RpR v1 (free)",match:{equals:"qwq-32b-arliai-rpr-v1:free"},prices:{}},{id:"qwq-32b-preview",name:"QwQ 32B Preview",match:{equals:"qwq-32b-preview"},prices:{input_mtok:.2,output_mtok:.2}},{id:"qwq-32b:free",name:"QwQ 32B (free)",match:{equals:"qwq-32b:free"},prices:{}},{id:"r1-1776",name:"R1 1776",match:{equals:"r1-1776"},prices:{input_mtok:2,output_mtok:8}},{id:"raifle/sorcererlm-8x22b",match:{equals:"raifle/sorcererlm-8x22b"},prices:{input_mtok:4.5,output_mtok:4.5}},{id:"reka-flash-3:free",name:"Flash 3 (free)",match:{equals:"reka-flash-3:free"},prices:{}},{id:"rekaai/reka-edge",name:"Reka Edge",match:{equals:"rekaai/reka-edge"},prices:{input_mtok:.1,output_mtok:.1}},{id:"rekaai/reka-flash-3",name:"Reka Flash 3",match:{equals:"rekaai/reka-flash-3"},prices:{input_mtok:.1,output_mtok:.2}},{id:"rekaai/reka-flash-3:free",match:{equals:"rekaai/reka-flash-3:free"},prices:{}},{id:"relace/relace-apply-3",name:"Relace Apply 3",match:{equals:"relace/relace-apply-3"},prices:{input_mtok:.85,output_mtok:1.25}},{id:"relace/relace-search",name:"Relace Search",match:{equals:"relace/relace-search"},prices:{input_mtok:1,output_mtok:3}},{id:"sao10k/fimbulvetr-11b-v2",match:{equals:"sao10k/fimbulvetr-11b-v2"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"sao10k/l3-euryale-70b",match:{equals:"sao10k/l3-euryale-70b"},prices:{input_mtok:1.48,output_mtok:1.48}},{id:"sao10k/l3-lunaris-8b",name:"Llama 3 8B Lunaris",match:{equals:"sao10k/l3-lunaris-8b"},prices:{input_mtok:.02,output_mtok:.05}},{id:"sao10k/l3.1-70b-hanami-x1",name:"Llama 3.1 70B Hanami x1",match:{equals:"sao10k/l3.1-70b-hanami-x1"},prices:{input_mtok:3,output_mtok:3}},{id:"sao10k/l3.1-euryale-70b",name:"Llama 3.1 Euryale 70B v2.2",match:{equals:"sao10k/l3.1-euryale-70b"},prices:{input_mtok:.7,output_mtok:.8}},{id:"sao10k/l3.3-euryale-70b",name:"Llama 3.3 Euryale 70B",match:{equals:"sao10k/l3.3-euryale-70b"},prices:{input_mtok:.7,output_mtok:.8}},{id:"sarvam-m:free",name:"Sarvam-M (free)",match:{equals:"sarvam-m:free"},prices:{}},{id:"scb10x/llama3.1-typhoon2-70b-instruct",match:{equals:"scb10x/llama3.1-typhoon2-70b-instruct"},prices:{input_mtok:.88,output_mtok:.88}},{id:"scb10x/llama3.1-typhoon2-8b-instruct",match:{equals:"scb10x/llama3.1-typhoon2-8b-instruct"},prices:{input_mtok:.18,output_mtok:.18}},{id:"shisa-ai/shisa-v2-llama3.3-70b:free",match:{equals:"shisa-ai/shisa-v2-llama3.3-70b:free"},prices:{}},{id:"shisa-v2-llama3.3-70b:free",name:"Shisa V2 Llama 3.3 70B (free)",match:{equals:"shisa-v2-llama3.3-70b:free"},prices:{}},{id:"sonar-reasoning",name:"Sonar Reasoning",match:{equals:"sonar-reasoning"},prices:{input_mtok:1,output_mtok:5}},{id:"sophosympatheia/midnight-rose-70b",match:{equals:"sophosympatheia/midnight-rose-70b"},prices:{input_mtok:.8,output_mtok:.8}},{id:"sophosympatheia/rogue-rose-103b-v0.2:free",match:{equals:"sophosympatheia/rogue-rose-103b-v0.2:free"},prices:{}},{id:"sorcererlm-8x22b",name:"SorcererLM 8x22B",match:{equals:"sorcererlm-8x22b"},prices:{input_mtok:4.5,output_mtok:4.5}},{id:"spotlight",name:"Spotlight",match:{equals:"spotlight"},prices:{input_mtok:.18,output_mtok:.18}},{id:"steelskull/l3.3-electra-r1-70b",match:{equals:"steelskull/l3.3-electra-r1-70b"},prices:{input_mtok:.7,output_mtok:.95}},{id:"stepfun/step-3.5-flash",name:"Step 3.5 Flash",match:{equals:"stepfun/step-3.5-flash"},prices:{input_mtok:.09,cache_read_mtok:.02,output_mtok:.3}},{id:"stepfun/step-3.7-flash",name:"Step 3.7 Flash",match:{equals:"stepfun/step-3.7-flash"},prices:{input_mtok:.2,cache_read_mtok:.04,output_mtok:1.15}},{id:"switchpoint/router",name:"Switchpoint Router",match:{equals:"switchpoint/router"},prices:{input_mtok:.85,output_mtok:3.4}},{id:"tencent/hunyuan-a13b-instruct",name:"Hunyuan A13B Instruct",match:{equals:"tencent/hunyuan-a13b-instruct"},prices:{input_mtok:.14,output_mtok:.57}},{id:"tencent/hy3-preview",name:"Hy3 preview",match:{equals:"tencent/hy3-preview"},prices:{input_mtok:.063,cache_read_mtok:.021,output_mtok:.21}},{id:"thedrummer/anubis-pro-105b-v1",match:{equals:"thedrummer/anubis-pro-105b-v1"},prices:{input_mtok:.8,output_mtok:1}},{id:"thedrummer/cydonia-24b-v4.1",name:"Cydonia 24B V4.1",match:{equals:"thedrummer/cydonia-24b-v4.1"},prices:{input_mtok:.3,cache_read_mtok:.15,output_mtok:.5}},{id:"thedrummer/rocinante-12b",name:"Rocinante 12B",match:{equals:"thedrummer/rocinante-12b"},prices:{input_mtok:.25,output_mtok:.5}},{id:"thedrummer/skyfall-36b-v2",name:"Skyfall 36B V2",match:{equals:"thedrummer/skyfall-36b-v2"},prices:{input_mtok:.5,output_mtok:.8}},{id:"thedrummer/unslopnemo-12b",match:{equals:"thedrummer/unslopnemo-12b"},prices:{input_mtok:.5,output_mtok:.5}},{id:"thudm/glm-4-32b:free",match:{equals:"thudm/glm-4-32b:free"},prices:{}},{id:"thudm/glm-z1-32b:free",match:{equals:"thudm/glm-z1-32b:free"},prices:{}},{id:"toppy-m-7b",name:"Toppy M 7B",match:{equals:"toppy-m-7b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"undi95/remm-slerp-l2-13b",name:"ReMM SLERP 13B",match:{equals:"undi95/remm-slerp-l2-13b"},prices:{input_mtok:.8,output_mtok:1.2}},{id:"undi95/toppy-m-7b",match:{equals:"undi95/toppy-m-7b"},prices:{input_mtok:.07,output_mtok:.07}},{id:"upstage/solar-pro-3",name:"Solar Pro 3",match:{equals:"upstage/solar-pro-3"},prices:{input_mtok:.15,cache_read_mtok:.015,output_mtok:.6}},{id:"valkyrie-49b-v1",name:"Valkyrie 49B V1",match:{equals:"valkyrie-49b-v1"},prices:{input_mtok:.5,output_mtok:.8}},{id:"virtuoso-medium-v2",name:"Virtuoso Medium V2",match:{equals:"virtuoso-medium-v2"},prices:{input_mtok:.5,output_mtok:.8}},{id:"writer/palmyra-x5",name:"Palmyra X5",match:{equals:"writer/palmyra-x5"},prices:{input_mtok:.6,output_mtok:6}},{id:"x-ai/grok-2-1212",match:{equals:"x-ai/grok-2-1212"},prices:{input_mtok:2,output_mtok:10}},{id:"x-ai/grok-2-vision-1212",match:{equals:"x-ai/grok-2-vision-1212"},prices:{input_mtok:2,output_mtok:10}},{id:"x-ai/grok-3-beta",match:{equals:"x-ai/grok-3-beta"},prices:{input_mtok:3,output_mtok:15}},{id:"x-ai/grok-3-mini-beta",match:{equals:"x-ai/grok-3-mini-beta"},prices:{input_mtok:.3,output_mtok:.5}},{id:"x-ai/grok-4-fast",match:{equals:"x-ai/grok-4-fast"},context_window:2e6,prices:{input_mtok:{base:.2,tiers:[{start:128e3,price:.4}]},cache_read_mtok:.05,output_mtok:{base:.5,tiers:[{start:128e3,price:1}]}}},{id:"x-ai/grok-4.1-fast:free",match:{equals:"x-ai/grok-4.1-fast:free"},context_window:2e6,prices:{}},{id:"x-ai/grok-4.20",name:"Grok 4.20",match:{equals:"x-ai/grok-4.20"},prices:{input_mtok:1.25,cache_read_mtok:.2,output_mtok:2.5}},{id:"x-ai/grok-4.20-multi-agent",name:"Grok 4.20 Multi-Agent",match:{equals:"x-ai/grok-4.20-multi-agent"},prices:{input_mtok:2,cache_read_mtok:.2,output_mtok:6}},{id:"x-ai/grok-4.3",name:"Grok 4.3",match:{equals:"x-ai/grok-4.3"},prices:{input_mtok:1.25,cache_read_mtok:.2,output_mtok:2.5}},{id:"x-ai/grok-beta",match:{equals:"x-ai/grok-beta"},prices:{input_mtok:5,output_mtok:15}},{id:"x-ai/grok-build-0.1",name:"Grok Build 0.1",match:{equals:"x-ai/grok-build-0.1"},prices:{input_mtok:1,cache_read_mtok:.2,output_mtok:2}},{id:"x-ai/grok-code-fast-1",match:{equals:"x-ai/grok-code-fast-1"},context_window:256e3,prices:{input_mtok:.2,cache_read_mtok:.02,output_mtok:1.5}},{id:"x-ai/grok-vision-beta",match:{equals:"x-ai/grok-vision-beta"},prices:{input_mtok:5,output_mtok:15}},{id:"xiaomi/mimo-v2-flash",name:"MiMo-V2-Flash",match:{equals:"xiaomi/mimo-v2-flash"},prices:{input_mtok:.1,cache_read_mtok:.01,output_mtok:.3}},{id:"xiaomi/mimo-v2.5",name:"MiMo-V2.5",match:{equals:"xiaomi/mimo-v2.5"},prices:{input_mtok:.14,cache_read_mtok:.0028,output_mtok:.28}},{id:"xiaomi/mimo-v2.5-pro",name:"MiMo-V2.5-Pro",match:{equals:"xiaomi/mimo-v2.5-pro"},prices:{input_mtok:.435,cache_read_mtok:.0036,output_mtok:.87}},{id:"xwin-lm/xwin-lm-70b",match:{equals:"xwin-lm/xwin-lm-70b"},prices:{input_mtok:3.75,output_mtok:3.75}},{id:"yi-large",name:"Yi Large",match:{equals:"yi-large"},prices:{input_mtok:3,output_mtok:3}},{id:"z-ai/glm-4.5",name:"GLM 4.5",match:{equals:"z-ai/glm-4.5"},prices:{input_mtok:.6,cache_read_mtok:.11,output_mtok:2.2}},{id:"z-ai/glm-4.5-air",name:"GLM 4.5 Air",match:{equals:"z-ai/glm-4.5-air"},prices:{input_mtok:.125,cache_read_mtok:.06,output_mtok:.85}},{id:"z-ai/glm-4.5v",name:"GLM 4.5V",match:{equals:"z-ai/glm-4.5v"},prices:{input_mtok:.6,cache_read_mtok:.11,output_mtok:1.8}},{id:"z-ai/glm-4.6",name:"GLM 4.6",match:{equals:"z-ai/glm-4.6"},prices:{input_mtok:.43,cache_read_mtok:.08,output_mtok:1.74}},{id:"z-ai/glm-4.6v",name:"GLM 4.6V",match:{equals:"z-ai/glm-4.6v"},prices:{input_mtok:.3,cache_read_mtok:.05,output_mtok:.9}},{id:"z-ai/glm-4.7",name:"GLM 4.7",match:{equals:"z-ai/glm-4.7"},prices:{input_mtok:.4,cache_read_mtok:.08,output_mtok:1.75}},{id:"z-ai/glm-4.7-flash",name:"GLM 4.7 Flash",match:{or:[{equals:"z-ai/glm-4.7-flash"},{equals:"z-ai/glm-4.7-flash-20260119"}]},prices:{input_mtok:.06,cache_read_mtok:.01,output_mtok:.4}},{id:"z-ai/glm-5",name:"GLM 5",match:{or:[{equals:"z-ai/glm-5"},{equals:"z-ai/glm-5-20260211"}]},prices:{input_mtok:.6,cache_read_mtok:.12,output_mtok:1.92}},{id:"z-ai/glm-5-turbo",name:"GLM 5 Turbo",match:{or:[{equals:"z-ai/glm-5-turbo"},{equals:"z-ai/glm-5-turbo-20260315"}]},prices:{input_mtok:1.2,cache_read_mtok:.24,output_mtok:4}},{id:"z-ai/glm-5.1",name:"GLM 5.1",match:{or:[{equals:"z-ai/glm-5.1"},{equals:"z-ai/glm-5.1-20260406"}]},prices:{input_mtok:.98,cache_read_mtok:.182,output_mtok:3.08}},{id:"z-ai/glm-5.2",name:"GLM 5.2",match:{or:[{equals:"z-ai/glm-5.2"},{equals:"z-ai/glm-5.2-20260616"}]},context_window:1048576,prices:{input_mtok:1.4,cache_read_mtok:.26,output_mtok:4.4}},{id:"~anthropic/claude-fable-latest",name:"Claude Fable Latest",match:{equals:"~anthropic/claude-fable-latest"},prices:{input_mtok:10,cache_write_mtok:12.5,cache_read_mtok:1,output_mtok:50}},{id:"~anthropic/claude-haiku-latest",name:"Anthropic Claude Haiku Latest",match:{equals:"~anthropic/claude-haiku-latest"},prices:{input_mtok:1,cache_write_mtok:1.25,cache_read_mtok:.1,output_mtok:5}},{id:"~anthropic/claude-opus-latest",name:"Claude Opus Latest",match:{equals:"~anthropic/claude-opus-latest"},prices:{input_mtok:5,cache_write_mtok:6.25,cache_read_mtok:.5,output_mtok:25}},{id:"~anthropic/claude-sonnet-latest",name:"Anthropic Claude Sonnet Latest",match:{equals:"~anthropic/claude-sonnet-latest"},prices:{input_mtok:3,cache_write_mtok:3.75,cache_read_mtok:.3,output_mtok:15}},{id:"~google/gemini-flash-latest",name:"Google Gemini Flash Latest",match:{equals:"~google/gemini-flash-latest"},prices:{input_mtok:1.5,cache_write_mtok:.08333333333333334,cache_read_mtok:.15,output_mtok:9}},{id:"~google/gemini-pro-latest",name:"Google Gemini Pro Latest",match:{equals:"~google/gemini-pro-latest"},prices:{input_mtok:2,cache_write_mtok:.375,cache_read_mtok:.2,output_mtok:12}},{id:"~moonshotai/kimi-latest",name:"MoonshotAI Kimi Latest",match:{equals:"~moonshotai/kimi-latest"},prices:{input_mtok:.68,cache_read_mtok:.34,output_mtok:3.41}},{id:"~openai/gpt-latest",name:"OpenAI GPT Latest",match:{equals:"~openai/gpt-latest"},prices:{input_mtok:5,cache_read_mtok:.5,output_mtok:30}},{id:"~openai/gpt-mini-latest",name:"OpenAI GPT Mini Latest",match:{equals:"~openai/gpt-mini-latest"},prices:{input_mtok:.75,cache_read_mtok:.075,output_mtok:4.5}}]},{id:"ovhcloud",name:"OVHcloud AI Endpoints",pricing_urls:["https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/models"],api_pattern:"https://oai\\.endpoints\\.kepler\\.ai\\.cloud\\.ovh\\.net",extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["prompt_tokens_details","audio_tokens"],dest:"input_audio_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"DeepSeek-R1-Distill-Llama-70B",name:"DeepSeek-R1-Distill-Llama-70B",match:{or:[{equals:"DeepSeek-R1-Distill-Llama-70B"},{equals:"deepseek-r1-distill-llama-70b"}]},context_window:131072,prices:{input_mtok:.74,output_mtok:.74}},{id:"Llama-3.1-8B-Instruct",name:"Llama-3.1-8B-Instruct",match:{or:[{equals:"Llama-3.1-8B-Instruct"},{equals:"llama-3.1-8b-instruct"}]},context_window:131072,prices:{input_mtok:.11,output_mtok:.11}},{id:"Meta-Llama-3_3-70B-Instruct",name:"Meta-Llama-3_3-70B-Instruct",match:{or:[{equals:"Meta-Llama-3_3-70B-Instruct"},{equals:"meta-llama-3_3-70b-instruct"}]},context_window:131072,prices:{input_mtok:.74,output_mtok:.74}},{id:"Mistral-7B-Instruct-v0.3",name:"Mistral-7B-Instruct-v0.3",match:{or:[{equals:"Mistral-7B-Instruct-v0.3"},{equals:"mistral-7b-instruct-v0.3"}]},context_window:65536,prices:{input_mtok:.11,output_mtok:.11}},{id:"Mistral-Nemo-Instruct-2407",name:"Mistral-Nemo-Instruct-2407",match:{or:[{equals:"Mistral-Nemo-Instruct-2407"},{equals:"mistral-nemo-instruct-2407"}]},context_window:65536,prices:{input_mtok:.14,output_mtok:.14}},{id:"Mistral-Small-3.2-24B-Instruct-2506",name:"Mistral-Small-3.2-24B-Instruct-2506",match:{or:[{equals:"Mistral-Small-3.2-24B-Instruct-2506"},{equals:"mistral-small-3.2-24b-instruct-2506"}]},context_window:131072,prices:{input_mtok:.1,output_mtok:.31}},{id:"Mixtral-8x7B-Instruct-v0.1",name:"Mixtral-8x7B-Instruct-v0.1",match:{or:[{equals:"Mixtral-8x7B-Instruct-v0.1"},{equals:"mixtral-8x7b-instruct-v0.1"}]},context_window:32768,prices:{input_mtok:.7,output_mtok:.7}},{id:"Qwen2.5-VL-72B-Instruct",name:"Qwen2.5-VL-72B-Instruct",match:{or:[{equals:"Qwen2.5-VL-72B-Instruct"},{equals:"qwen2.5-vl-72b-instruct"}]},context_window:32768,prices:{input_mtok:1.01,output_mtok:1.01}},{id:"Qwen3-32B",name:"Qwen3-32B",match:{or:[{equals:"Qwen3-32B"},{equals:"qwen3-32b"}]},context_window:32768,prices:{input_mtok:.09,output_mtok:.25}},{id:"Qwen3-Coder-30B-A3B-Instruct",name:"Qwen3-Coder-30B-A3B-Instruct",match:{or:[{equals:"Qwen3-Coder-30B-A3B-Instruct"},{equals:"qwen3-coder-30b-a3b-instruct"}]},context_window:262144,prices:{input_mtok:.07,output_mtok:.26}},{id:"bge-base-en-v1.5",name:"bge-base-en-v1.5",match:{equals:"bge-base-en-v1.5"},context_window:512,prices:{input_mtok:.01}},{id:"bge-m3",name:"bge-m3",match:{equals:"bge-m3"},context_window:8192,prices:{input_mtok:.01}},{id:"bge-multilingual-gemma2",name:"bge-multilingual-gemma2",match:{equals:"bge-multilingual-gemma2"},context_window:8192,prices:{input_mtok:.01}},{id:"gpt-oss-120b",name:"gpt-oss-120b",match:{equals:"gpt-oss-120b"},context_window:131072,prices:{input_mtok:.09,output_mtok:.47}},{id:"gpt-oss-20b",name:"gpt-oss-20b",match:{equals:"gpt-oss-20b"},context_window:131072,prices:{input_mtok:.05,output_mtok:.18}}]},{id:"perplexity",name:"Perplexity",pricing_urls:["https://docs.perplexity.ai/guides/pricing"],api_pattern:"https://api\\.perplexity\\.ai",price_comments:"Prices per request vary based on usage, this is not represented here, instead we just take the highest price shown for `requests_kcount`.",models:[{id:"llama-3.1-sonar-large-128k-online",name:"Llama 3.1 Sonar 70B Online",description:"Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance.",match:{equals:"llama-3.1-sonar-large-128k-online"},prices:{input_mtok:1,output_mtok:1}},{id:"llama-3.1-sonar-small-128k-online",name:"Llama 3.1 Sonar 8B Online",description:"Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance.",match:{equals:"llama-3.1-sonar-small-128k-online"},prices:{input_mtok:.2,output_mtok:.2}},{id:"r1-1776",name:"R1 1776",description:"R1 1776 is a version of DeepSeek-R1 that has been post-trained to remove censorship constraints related to topics restricted by the Chinese government. The model retains its original reasoning capabilities while providing direct responses to a wider range of queries. R1 1776 is an offline chat model that does not use the perplexity search subsystem.",match:{equals:"r1-1776"},prices:{input_mtok:2,output_mtok:8}},{id:"sonar",name:"Sonar",description:"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features optimized for speed.",match:{equals:"sonar"},prices:{input_mtok:1,output_mtok:1,requests_kcount:12}},{id:"sonar-deep-research",name:"Sonar Deep Research",description:"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers information. This enables comprehensive report generation across domains like finance, technology, health, and current events.",match:{equals:"sonar-deep-research"},prices:{input_mtok:2,output_mtok:8}},{id:"sonar-pro",name:"Sonar Pro",description:"Note: Sonar Pro pricing includes Perplexity search pricing. See details here",match:{equals:"sonar-pro"},prices:{input_mtok:3,output_mtok:15,requests_kcount:14}},{id:"sonar-pro-search",name:"Sonar Pro Search",description:"Sonar Pro Search is Perplexity's advanced agentic search system for deeper reasoning and analysis.",match:{equals:"sonar-pro-search"},price_comments:"Imported from OpenRouter pricing; verify against Perplexity pricing when native API pricing is published.",prices:{input_mtok:3,output_mtok:15}},{id:"sonar-reasoning",name:"Sonar Reasoning",description:"Sonar Reasoning is a reasoning model provided by Perplexity based on DeepSeek R1.",match:{equals:"sonar-reasoning"},prices:{input_mtok:1,output_mtok:5,requests_kcount:12}},{id:"sonar-reasoning-pro",name:"Sonar Reasoning Pro",description:"Sonar Pro pricing includes Perplexity search pricing.",match:{equals:"sonar-reasoning-pro"},prices:{input_mtok:2,output_mtok:8,requests_kcount:14}}]},{id:"together",name:"Together AI",pricing_urls:["https://www.together.ai/pricing"],api_pattern:"https://api\\.together\\.xyz",provider_match:{or:[{equals:"together-ai"},{equals:"together_ai"}]},models:[{id:"Austism/chronos-hermes-13b",match:{equals:"Austism/chronos-hermes-13b"},prices:{input_mtok:.3,output_mtok:.3}},{id:"Gryphe/MythoMax-L2-13b",match:{equals:"Gryphe/MythoMax-L2-13b"},prices:{input_mtok:.3,output_mtok:.3}},{id:"Nexusflow/NexusRaven-V2-13B",match:{equals:"Nexusflow/NexusRaven-V2-13B"},prices:{input_mtok:.3,output_mtok:.3}},{id:"NousResearch/Nous-Capybara-7B-V1p9",match:{equals:"NousResearch/Nous-Capybara-7B-V1p9"},prices:{input_mtok:.2,output_mtok:.2}},{id:"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",match:{equals:"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO"},prices:{input_mtok:.9,output_mtok:.9}},{id:"NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT",match:{equals:"NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT"},prices:{input_mtok:.9,output_mtok:.9}},{id:"NousResearch/Nous-Hermes-2-Yi-34B",match:{equals:"NousResearch/Nous-Hermes-2-Yi-34B"},prices:{input_mtok:.8,output_mtok:.8}},{id:"NousResearch/Nous-Hermes-Llama2-13b",match:{equals:"NousResearch/Nous-Hermes-Llama2-13b"},prices:{input_mtok:.225,output_mtok:.225}},{id:"NousResearch/Nous-Hermes-llama-2-7b",match:{equals:"NousResearch/Nous-Hermes-llama-2-7b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"Open-Orca/Mistral-7B-OpenOrca",match:{equals:"Open-Orca/Mistral-7B-OpenOrca"},prices:{input_mtok:.2,output_mtok:.2}},{id:"Qwen/Qwen1.5-0.5B",match:{or:[{equals:"Qwen/Qwen1.5-0.5B"},{equals:"Qwen/Qwen1.5-0.5B-Chat"}]},prices:{input_mtok:.1,output_mtok:.1}},{id:"Qwen/Qwen1.5-1.8B",match:{or:[{equals:"Qwen/Qwen1.5-1.8B"},{equals:"Qwen/Qwen1.5-1.8B-Chat"}]},prices:{input_mtok:.1,output_mtok:.1}},{id:"Qwen/Qwen1.5-14B",match:{or:[{equals:"Qwen/Qwen1.5-14B"},{equals:"Qwen/Qwen1.5-14B-Chat"}]},prices:{input_mtok:.3,output_mtok:.3}},{id:"Qwen/Qwen1.5-4B",match:{or:[{equals:"Qwen/Qwen1.5-4B"},{equals:"Qwen/Qwen1.5-4B-Chat"}]},prices:{input_mtok:.1,output_mtok:.1}},{id:"Qwen/Qwen1.5-72B",match:{equals:"Qwen/Qwen1.5-72B"},prices:{input_mtok:.9,output_mtok:.9}},{id:"Qwen/Qwen1.5-7B",match:{or:[{equals:"Qwen/Qwen1.5-7B"},{equals:"Qwen/Qwen1.5-7B-Chat"}]},prices:{input_mtok:.2,output_mtok:.2}},{id:"Undi95/ReMM-SLERP-L2-13B",match:{equals:"Undi95/ReMM-SLERP-L2-13B"},prices:{input_mtok:.3,output_mtok:.3}},{id:"Undi95/Toppy-M-7B",match:{equals:"Undi95/Toppy-M-7B"},prices:{input_mtok:.2,output_mtok:.2}},{id:"WizardLM/WizardLM-13B-V1.2",match:{equals:"WizardLM/WizardLM-13B-V1.2"},prices:{input_mtok:.3,output_mtok:.3}},{id:"allenai/OLMo-7B",match:{or:[{equals:"allenai/OLMo-7B"},{equals:"allenai/OLMo-7B-Instruct"},{equals:"allenai/OLMo-7B-Twin-2T"}]},prices:{input_mtok:.2,output_mtok:.2}},{id:"codellama/CodeLlama-13b-Instruct-hf",match:{equals:"codellama/CodeLlama-13b-Instruct-hf"},prices:{input_mtok:.225,output_mtok:.225}},{id:"codellama/CodeLlama-34b-Instruct-hf",match:{equals:"codellama/CodeLlama-34b-Instruct-hf"},prices:{input_mtok:.776,output_mtok:.776}},{id:"codellama/CodeLlama-70b-Instruct-hf",match:{equals:"codellama/CodeLlama-70b-Instruct-hf"},prices:{input_mtok:.9,output_mtok:.9}},{id:"codellama/CodeLlama-7b-Instruct-hf",match:{equals:"codellama/CodeLlama-7b-Instruct-hf"},prices:{input_mtok:.2,output_mtok:.2}},{id:"deepseek-ai/deepseek-coder-33b-instruct",match:{equals:"deepseek-ai/deepseek-coder-33b-instruct"},prices:{input_mtok:.8,output_mtok:.8}},{id:"garage-bAInd/Platypus2-70B-instruct",match:{equals:"garage-bAInd/Platypus2-70B-instruct"},prices:{input_mtok:.9,output_mtok:.9}},{id:"google/gemma-2b",match:{or:[{equals:"google/gemma-2b"},{equals:"google/gemma-2b-it"}]},prices:{input_mtok:.1,output_mtok:.1}},{id:"google/gemma-7b",match:{or:[{equals:"google/gemma-7b"},{equals:"google/gemma-7b-it"}]},prices:{input_mtok:.2,output_mtok:.2}},{id:"lmsys/vicuna-13b-v1.5",match:{equals:"lmsys/vicuna-13b-v1.5"},prices:{input_mtok:.3,output_mtok:.3}},{id:"lmsys/vicuna-7b-v1.5",match:{equals:"lmsys/vicuna-7b-v1.5"},prices:{input_mtok:.2,output_mtok:.2}},{id:"meta-llama/Llama-2-13b-chat-hf",match:{equals:"meta-llama/Llama-2-13b-chat-hf"},prices:{input_mtok:.225,output_mtok:.225}},{id:"meta-llama/Llama-2-70b-chat-hf",match:{equals:"meta-llama/Llama-2-70b-chat-hf"},prices:{input_mtok:.9,output_mtok:.9}},{id:"meta-llama/Llama-2-7b-chat-hf",match:{equals:"meta-llama/Llama-2-7b-chat-hf"},prices:{input_mtok:.2,output_mtok:.2}},{id:"meta-llama/Llama-3-70b-chat-hf",match:{equals:"meta-llama/Llama-3-70b-chat-hf"},prices:{input_mtok:.9,output_mtok:.9}},{id:"meta-llama/Llama-3-8b-chat-hf",match:{equals:"meta-llama/Llama-3-8b-chat-hf"},prices:{input_mtok:.2,output_mtok:.2}},{id:"meta-llama/Llama-3.3-70B-Instruct-Turbo",match:{equals:"meta-llama/Llama-3.3-70B-Instruct-Turbo"},prices:{input_mtok:.88,output_mtok:.88}},{id:"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",match:{equals:"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"},prices:{input_mtok:.27,output_mtok:.85}},{id:"meta-llama/Llama-4-Scout-17B-16E-Instruct",match:{equals:"meta-llama/Llama-4-Scout-17B-16E-Instruct"},prices:{input_mtok:.18,output_mtok:.59}},{id:"meta-llama/Meta-Llama-3-70B-Instruct-Lite",match:{equals:"meta-llama/Meta-Llama-3-70B-Instruct-Lite"},prices:{input_mtok:.54,output_mtok:.54}},{id:"meta-llama/Meta-Llama-3-70B-Instruct-Turbo",match:{equals:"meta-llama/Meta-Llama-3-70B-Instruct-Turbo"},prices:{input_mtok:.88,output_mtok:.88}},{id:"meta-llama/Meta-Llama-3-8B-Instruct-Lite",match:{equals:"meta-llama/Meta-Llama-3-8B-Instruct-Lite"},prices:{input_mtok:.1,output_mtok:.1}},{id:"meta-llama/Meta-Llama-3-8B-Instruct-Turbo",match:{equals:"meta-llama/Meta-Llama-3-8B-Instruct-Turbo"},prices:{input_mtok:.18,output_mtok:.18}},{id:"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",match:{equals:"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo"},prices:{input_mtok:3.5,output_mtok:3.5}},{id:"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",match:{equals:"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo"},prices:{input_mtok:.88,output_mtok:.88}},{id:"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",match:{equals:"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo"},prices:{input_mtok:.18,output_mtok:.18}},{id:"meta-llama/Meta-Llama-3.3-70B-Instruct-Turbo",match:{equals:"meta-llama/Meta-Llama-3.3-70B-Instruct-Turbo"},prices:{input_mtok:.88,output_mtok:.88}},{id:"microsoft/WizardLM-2-8x22B",match:{equals:"microsoft/WizardLM-2-8x22B"},prices:{input_mtok:1.2,output_mtok:1.2}},{id:"microsoft/phi-2",match:{equals:"microsoft/phi-2"},prices:{input_mtok:.1,output_mtok:.1}},{id:"mistralai/Mistral-7B-Instruct-v0.1",match:{equals:"mistralai/Mistral-7B-Instruct-v0.1"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistralai/Mistral-7B-Instruct-v0.2",match:{equals:"mistralai/Mistral-7B-Instruct-v0.2"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistralai/Mistral-7B-v0.1",match:{equals:"mistralai/Mistral-7B-v0.1"},prices:{input_mtok:.2,output_mtok:.2}},{id:"mistralai/Mixtral-8x22B-Instruct-v0.1",match:{equals:"mistralai/Mixtral-8x22B-Instruct-v0.1"},prices:{input_mtok:2.4,output_mtok:2.4}},{id:"mistralai/Mixtral-8x7B-Instruct-v0.1",match:{equals:"mistralai/Mixtral-8x7B-Instruct-v0.1"},prices:{input_mtok:.9,output_mtok:.9}},{id:"mistralai/Mixtral-8x7B-v0.1",match:{equals:"mistralai/Mixtral-8x7B-v0.1"},prices:{input_mtok:.9,output_mtok:.9}},{id:"openchat/openchat-3.5-1210",match:{equals:"openchat/openchat-3.5-1210"},prices:{input_mtok:.2,output_mtok:.2}},{id:"snorkelai/Snorkel-Mistral-PairRM-DPO",match:{equals:"snorkelai/Snorkel-Mistral-PairRM-DPO"},prices:{input_mtok:.2,output_mtok:.2}},{id:"teknium/OpenHermes-2-Mistral-7B",match:{equals:"teknium/OpenHermes-2-Mistral-7B"},prices:{input_mtok:.2,output_mtok:.2}},{id:"teknium/OpenHermes-2p5-Mistral-7B",match:{equals:"teknium/OpenHermes-2p5-Mistral-7B"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/GPT-JT-Moderation-6B",match:{equals:"togethercomputer/GPT-JT-Moderation-6B"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/Llama-2-7B-32K-Instruct",match:{equals:"togethercomputer/Llama-2-7B-32K-Instruct"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/RedPajama-INCITE-7B-Base",match:{equals:"togethercomputer/RedPajama-INCITE-7B-Base"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/RedPajama-INCITE-7B-Chat",match:{equals:"togethercomputer/RedPajama-INCITE-7B-Chat"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/RedPajama-INCITE-7B-Instruct",match:{equals:"togethercomputer/RedPajama-INCITE-7B-Instruct"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/RedPajama-INCITE-Base-3B-v1",match:{equals:"togethercomputer/RedPajama-INCITE-Base-3B-v1"},prices:{input_mtok:.1,output_mtok:.1}},{id:"togethercomputer/RedPajama-INCITE-Chat-3B-v1",match:{equals:"togethercomputer/RedPajama-INCITE-Chat-3B-v1"},prices:{input_mtok:.1,output_mtok:.1}},{id:"togethercomputer/RedPajama-INCITE-Instruct-3B-v1",match:{equals:"togethercomputer/RedPajama-INCITE-Instruct-3B-v1"},prices:{input_mtok:.1,output_mtok:.1}},{id:"togethercomputer/StripedHyena-Hessian-7B",match:{equals:"togethercomputer/StripedHyena-Hessian-7B"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/StripedHyena-Nous-7B",match:{equals:"togethercomputer/StripedHyena-Nous-7B"},prices:{input_mtok:.2,output_mtok:.2}},{id:"togethercomputer/alpaca-7b",match:{equals:"togethercomputer/alpaca-7b"},prices:{input_mtok:.2,output_mtok:.2}},{id:"upstage/SOLAR-10.7B-Instruct-v1.0",match:{equals:"upstage/SOLAR-10.7B-Instruct-v1.0"},prices:{input_mtok:.3,output_mtok:.3}},{id:"zero-one-ai/Yi-34B",match:{equals:"zero-one-ai/Yi-34B"},prices:{input_mtok:.8,output_mtok:.8}},{id:"zero-one-ai/Yi-6B",match:{equals:"zero-one-ai/Yi-6B"},prices:{input_mtok:.2,output_mtok:.2}}]},{id:"voyageai",name:"Voyage AI",pricing_urls:["https://docs.voyageai.com/docs/pricing"],api_pattern:"https://api\\.voyageai\\.com",price_comments:"Voyage AI bills per input token only; embedding models produce vectors rather than completion tokens, so there is no output price. The Batch API offers a 33% discount. This file covers text embedding models only; rerankers and multimodal embedding models are not included.",model_match:{starts_with:"voyage-"},provider_match:{contains:"voyage"},models:[{id:"voyage-01",name:"Voyage 01",match:{equals:"voyage-01"},prices:{input_mtok:.1},deprecated:!0},{id:"voyage-02",name:"Voyage 02",match:{equals:"voyage-02"},prices:{input_mtok:.1},deprecated:!0},{id:"voyage-2",name:"Voyage 2",match:{equals:"voyage-2"},prices:{input_mtok:.1}},{id:"voyage-3",name:"Voyage 3",description:"General-purpose text embedding model optimized for retrieval quality and cost.",match:{equals:"voyage-3"},prices:{input_mtok:.06}},{id:"voyage-3-large",name:"Voyage 3 Large",match:{equals:"voyage-3-large"},prices:{input_mtok:.18}},{id:"voyage-3-lite",name:"Voyage 3 Lite",match:{equals:"voyage-3-lite"},prices:{input_mtok:.02}},{id:"voyage-3.5",name:"Voyage 3.5",description:"General-purpose text embedding model optimized for retrieval quality and cost.",match:{equals:"voyage-3.5"},prices:{input_mtok:.06}},{id:"voyage-3.5-lite",name:"Voyage 3.5 Lite",description:"Latency- and cost-optimized variant of voyage-3.5.",match:{equals:"voyage-3.5-lite"},prices:{input_mtok:.02}},{id:"voyage-4",name:"Voyage 4",description:"General-purpose text embedding model balancing retrieval quality and cost.",match:{equals:"voyage-4"},prices:{input_mtok:.06}},{id:"voyage-4-large",name:"Voyage 4 Large",description:"Highest-quality general-purpose text embedding model in the Voyage 4 family.",match:{equals:"voyage-4-large"},prices:{input_mtok:.12}},{id:"voyage-4-lite",name:"Voyage 4 Lite",description:"Latency- and cost-optimized text embedding model in the Voyage 4 family.",match:{equals:"voyage-4-lite"},prices:{input_mtok:.02}},{id:"voyage-code-2",name:"Voyage Code 2",description:"Embedding model optimized for code retrieval.",match:{equals:"voyage-code-2"},prices:{input_mtok:.12}},{id:"voyage-code-3",name:"Voyage Code 3",description:"Embedding model optimized for code retrieval.",match:{equals:"voyage-code-3"},prices:{input_mtok:.18}},{id:"voyage-context-3",name:"Voyage Context 3",description:"Contextualized chunk embedding model that encodes chunks together with full-document context.",match:{equals:"voyage-context-3"},prices:{input_mtok:.18}},{id:"voyage-finance-2",name:"Voyage Finance 2",description:"Embedding model optimized for finance-domain retrieval.",match:{equals:"voyage-finance-2"},prices:{input_mtok:.12}},{id:"voyage-large-2",name:"Voyage Large 2",match:{equals:"voyage-large-2"},prices:{input_mtok:.12}},{id:"voyage-large-2-instruct",name:"Voyage Large 2 Instruct",match:{equals:"voyage-large-2-instruct"},prices:{input_mtok:.12}},{id:"voyage-law-2",name:"Voyage Law 2",description:"Embedding model optimized for legal-domain retrieval.",match:{equals:"voyage-law-2"},prices:{input_mtok:.12}},{id:"voyage-lite-01",name:"Voyage Lite 01",match:{equals:"voyage-lite-01"},prices:{input_mtok:.1},deprecated:!0},{id:"voyage-lite-01-instruct",name:"Voyage Lite 01 Instruct",match:{equals:"voyage-lite-01-instruct"},prices:{input_mtok:.1},deprecated:!0},{id:"voyage-lite-02-instruct",name:"Voyage Lite 02 Instruct",match:{equals:"voyage-lite-02-instruct"},prices:{input_mtok:.1},deprecated:!0},{id:"voyage-multilingual-2",name:"Voyage Multilingual 2",match:{equals:"voyage-multilingual-2"},prices:{input_mtok:.12}}]},{id:"x-ai",name:"X AI",pricing_urls:["https://docs.x.ai/docs/models"],api_pattern:"https://api\\.x\\.ai",model_match:{contains:"grok"},provider_match:{equals:"xai"},extractors:[{api_flavor:"default",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:"cached_prompt_text_tokens",dest:"cache_read_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]},{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:["completion_tokens_details","audio_tokens"],dest:"output_audio_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"grok-2-1212",name:"Grok 2 1212",description:"(deprecated) Grok 2 1212 introduces significant enhancements to accuracy, instruction adherence, and multilingual support, making it a powerful and flexible choice for developers seeking a highly steerable, intelligent model.",match:{or:[{equals:"grok-2-1212"},{equals:"grok-2"},{equals:"grok-2-latest"}]},context_window:32768,prices:{input_mtok:2,output_mtok:10},deprecated:!0},{id:"grok-2-vision-1212",name:"Grok 2 Vision 1212",description:"Our multimodal model that processes documents, diagrams, charts, screenshots, and photographs.",match:{or:[{equals:"grok-2-vision-1212"},{equals:"grok-2-vision"},{equals:"grok-2-vision-latest"}]},context_window:32768,prices:{input_mtok:2,output_mtok:10}},{id:"grok-3",name:"Grok 3",description:"Flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science.",match:{or:[{equals:"grok-3"},{equals:"grok-3-latest"},{equals:"grok-3-beta"}]},context_window:131072,prices:{input_mtok:3,cache_read_mtok:.75,output_mtok:15}},{id:"grok-3-fast",name:"Grok 3 Fast",description:"Excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science.",match:{or:[{equals:"grok-3-fast"},{equals:"grok-3-fast-latest"},{equals:"grok-3-fast-beta"}]},context_window:131072,prices:{input_mtok:5,cache_read_mtok:1.25,output_mtok:25}},{id:"grok-3-mini",name:"Grok 3 Mini",description:"A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.",match:{or:[{equals:"grok-3-mini"},{equals:"grok-3-mini-beta"},{equals:"grok-3-mini-latest"}]},context_window:131072,prices:{input_mtok:.3,cache_read_mtok:.075,output_mtok:.5}},{id:"grok-3-mini-fast",name:"Grok 3 Mini Fast",description:"A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.",match:{or:[{equals:"grok-3-mini-fast"},{equals:"grok-3-mini-fast-beta"},{equals:"grok-3-mini-fast-latest"}]},context_window:131072,prices:{input_mtok:.6,cache_read_mtok:.15,output_mtok:4}},{id:"grok-4-0709",name:"Grok 4",description:"A flagship model, offering unparalleled performance in natural language, math and reasoning - the perfect jack of all trades.",match:{or:[{equals:"grok-4-0709"},{equals:"grok-4"},{equals:"grok-4-latest"}]},context_window:256e3,prices:{input_mtok:3,cache_read_mtok:.75,output_mtok:15}},{id:"grok-4-1-fast-non-reasoning",name:"Grok 4.1 Fast Non-Reasoning",description:"A frontier multimodal model optimized specifically for high-performance agentic tool calling.",match:{or:[{equals:"grok-4-1-fast-non-reasoning"},{equals:"grok-4-1-fast-non-reasoning-latest"}]},context_window:2e6,prices:{input_mtok:.2,cache_read_mtok:.05,output_mtok:.5}},{id:"grok-4-1-fast-reasoning",name:"Grok 4.1 Fast Reasoning",description:"A frontier multimodal model optimized specifically for high-performance agentic tool calling.",match:{or:[{equals:"grok-4-1-fast"},{equals:"grok-4-1-fast-reasoning"},{equals:"grok-4-1-fast-reasoning-latest"}]},context_window:2e6,prices:{input_mtok:.2,cache_read_mtok:.05,output_mtok:.5}},{id:"grok-4-fast-non-reasoning",name:"Grok 4 Fast Non-Reasoning",description:"A frontier multimodal model optimized specifically for high-performance agentic tool calling.",match:{or:[{equals:"grok-4-fast-non-reasoning"},{equals:"grok-4-fast-non-reasoning-latest"}]},context_window:2e6,prices:{input_mtok:.2,cache_read_mtok:.05,output_mtok:.5}},{id:"grok-4-fast-reasoning",name:"Grok 4 Fast Reasoning",description:"A frontier multimodal model optimized specifically for high-performance agentic tool calling.",match:{or:[{equals:"grok-4-fast"},{equals:"grok-4-fast-reasoning"},{equals:"grok-4-fast-reasoning-latest"}]},context_window:2e6,prices:{input_mtok:.2,cache_read_mtok:.05,output_mtok:.5}},{id:"grok-4.20",name:"Grok 4.20",description:"Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines low hallucination rates with strict prompt adherence.",match:{equals:"grok-4.20"},prices:{input_mtok:1.25,cache_read_mtok:.2,output_mtok:2.5}},{id:"grok-4.20-multi-agent",name:"Grok 4.20 Multi-Agent",description:"Grok 4.20 Multi-Agent is a variant of xAI's Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information.",match:{equals:"grok-4.20-multi-agent"},prices:{input_mtok:2,cache_read_mtok:.2,output_mtok:6}},{id:"grok-4.3",name:"Grok 4.3",description:"Most advanced flagship model, leading the industry in non-hallucination rate, agentic tool calling, and instruction following capabilities. Supports text and image inputs with text outputs, function calling, structured outputs, and reasoning.",match:{or:[{equals:"grok-4.3"},{equals:"grok-4.3-latest"},{equals:"grok-latest"}]},context_window:1e6,prices:{input_mtok:1.25,cache_read_mtok:.2,output_mtok:2.5}},{id:"grok-build-0.1",name:"Grok Build 0.1",description:"Grok Build 0.1 is xAI's fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding.",match:{equals:"grok-build-0.1"},prices:{input_mtok:1,cache_read_mtok:.2,output_mtok:2}},{id:"grok-code-fast-1",name:"Grok Code Fast 1",description:"A speedy and economical reasoning model that excels at agentic coding.",match:{or:[{equals:"grok-code-fast"},{equals:"grok-code-fast-1"},{equals:"grok-code-fast-1-0825"}]},context_window:256e3,prices:{input_mtok:.2,cache_read_mtok:.02,output_mtok:1.5}}]},{id:"zhipuai",name:"Zhipu AI",pricing_urls:["https://open.bigmodel.cn/pricing","https://docs.bigmodel.cn/cn/guide/start/model-overview"],api_pattern:"https://open\\.bigmodel\\.cn",price_comments:"Prices sourced from Zhipu AI open platform pricing (CNY, open.bigmodel.cn/pricing), converted to USD at 1 USD = 7.25 CNY (May/June 2026). Zhipu AI does not publish USD prices; CNY is the only billing currency. Flagship models (GLM-4.5-Air, GLM-4.7, GLM-5 series) have tiered pricing by input/output length; prices shown are for the cheapest tier ([0, 32k) input / [0, 0.2k) output where applicable). GLM-4 standard inference models (GLM-4-Air, GLM-4-Plus, etc.) bill input and output tokens at the same per-token rate per their pricing page. Cache write is temporarily free for flagship models (limited-time promotion, not included).",model_match:{or:[{starts_with:"GLM-"},{starts_with:"glm-"}]},extractors:[{api_flavor:"chat",root:"usage",model_path:"model",mappings:[{path:"prompt_tokens",dest:"input_tokens",required:!0},{path:["prompt_tokens_details","cached_tokens"],dest:"cache_read_tokens",required:!1},{path:"completion_tokens",dest:"output_tokens",required:!0}]}],models:[{id:"GLM-4-Air",name:"GLM-4-Air",description:"High-performance GLM-4 model with context caching. 128,000 token context window. Input and output billed at the same per-token rate.",match:{or:[{equals:"GLM-4-Air"},{equals:"glm-4-air"}]},context_window:128e3,prices:{input_mtok:.069,cache_read_mtok:.034,output_mtok:.069}},{id:"GLM-4-AirX",name:"GLM-4-AirX",description:"Fastest GLM-4 model. 8,000 token context window. Does not support context caching. Input and output billed at the same per-token rate.",match:{or:[{equals:"GLM-4-AirX"},{equals:"glm-4-airx"}]},context_window:8e3,prices:{input_mtok:1.379,output_mtok:1.379}},{id:"GLM-4-Assistant",name:"GLM-4-Assistant",description:"GLM-4 agent/assistant model. 128,000 token context window. Does not support context caching. Input and output billed at the same per-token rate.",match:{or:[{equals:"GLM-4-Assistant"},{equals:"glm-4-assistant"}]},context_window:128e3,prices:{input_mtok:.69,output_mtok:.69}},{id:"GLM-4-FlashX-250414",name:"GLM-4-FlashX-250414",description:"Fast and cheap GLM-4 model with context caching. 128,000 token context window. Input and output billed at the same per-token rate.",match:{or:[{equals:"GLM-4-FlashX-250414"},{equals:"glm-4-flashx-250414"}]},context_window:128e3,prices:{input_mtok:.014,cache_read_mtok:.007,output_mtok:.014}},{id:"GLM-4-Long",name:"GLM-4-Long",description:"GLM-4 model optimized for long inputs with context caching. 1,000,000 token context window. Input and output billed at the same per-token rate.",match:{or:[{equals:"GLM-4-Long"},{equals:"glm-4-long"}]},context_window:1e6,prices:{input_mtok:.138,cache_read_mtok:.069,output_mtok:.138}},{id:"GLM-4-Plus",name:"GLM-4-Plus",description:"Flagship GLM-4 model with context caching. 128,000 token context window. Input and output billed at the same per-token rate.",match:{or:[{equals:"GLM-4-Plus"},{equals:"glm-4-plus"}]},context_window:128e3,prices:{input_mtok:.69,cache_read_mtok:.345,output_mtok:.69}},{id:"GLM-4.5-Air",name:"GLM-4.5-Air",description:"Zhipu AI's GLM-4.5-Air flagship model with context caching. 128,000 token context window. Tiered pricing; prices shown for [0, 32k) input / [0, 0.2k) output tier.",match:{or:[{equals:"GLM-4.5-Air"},{equals:"glm-4.5-air"}]},context_window:128e3,prices:{input_mtok:.11,cache_read_mtok:.022,output_mtok:.276}},{id:"GLM-4.7",name:"GLM-4.7",description:"Zhipu AI's GLM-4.7 flagship model with context caching. 200,000 token context window. Tiered pricing; prices shown for [0, 32k) input / [0, 0.2k) output tier.",match:{or:[{equals:"GLM-4.7"},{equals:"glm-4.7"}]},context_window:2e5,prices:{input_mtok:.276,cache_read_mtok:.055,output_mtok:1.103}},{id:"GLM-4.7-FlashX",name:"GLM-4.7-FlashX",description:"Fast and affordable GLM-4.7 model with context caching. 200,000 token context window.",match:{or:[{equals:"GLM-4.7-FlashX"},{equals:"glm-4.7-flashx"}]},context_window:2e5,prices:{input_mtok:.069,cache_read_mtok:.014,output_mtok:.414}},{id:"GLM-5",name:"GLM-5",description:"Zhipu AI GLM-5 model with context caching. 200,000 token context window. Tiered pricing; prices shown for [0, 32k) input tier.",match:{or:[{equals:"GLM-5"},{equals:"glm-5"}]},context_window:2e5,prices:{input_mtok:.552,cache_read_mtok:.138,output_mtok:2.483}},{id:"GLM-5-Turbo",name:"GLM-5-Turbo",description:"Zhipu AI GLM-5 Turbo model with context caching. 200,000 token context window. Tiered pricing; prices shown for [0, 32k) input tier.",match:{or:[{equals:"GLM-5-Turbo"},{equals:"glm-5-turbo"}]},context_window:2e5,prices:{input_mtok:.69,cache_read_mtok:.166,output_mtok:3.034}},{id:"GLM-5.1",name:"GLM-5.1",description:"Zhipu AI flagship model supporting long-horizon tasks, structured output, function calling, and context caching. 200,000 token context window. Tiered pricing; prices shown for [0, 32k) input tier.",match:{or:[{equals:"GLM-5.1"},{equals:"glm-5.1"},{equals:"GLM-5.1-20260406"},{equals:"glm-5.1-20260406"}]},context_window:2e5,prices:{input_mtok:.828,cache_read_mtok:.179,output_mtok:3.31}},{id:"GLM-5.2",name:"GLM-5.2",description:"Zhipu AI's latest flagship model supporting 1,000,000 token context, long-horizon coding tasks, structured output, function calling, and context caching.",match:{or:[{equals:"GLM-5.2"},{equals:"glm-5.2"}]},context_window:1e6,prices:{input_mtok:1.103,cache_read_mtok:.276,output_mtok:3.862}}]}];function T(e,t,i){if(t<=0)return 0;let a=e.base;for(const o of e.tiers)i>o.start&&(a=o.price);return a*t/1e6}function d(e,t,i,a){return e===void 0||t===void 0?0:typeof e=="number"?e*t/1e6:T(e,t,a)}function S(e,t){let i=0,a=0;const o=e.input_tokens??0,r=e.cache_read_tokens??0,m=e.cache_write_tokens??0,n=e.cache_audio_read_tokens??0,s=e.input_audio_tokens??0,c=e.output_audio_tokens??0,u=t.cache_audio_read_mtok===void 0?0:n,p=t.cache_audio_read_mtok===void 0&&t.cache_read_mtok!==void 0?n:0;let l=0;if(t.input_audio_mtok!==void 0&&(l=s-u-p),l<0)throw new Error("cache_audio_read_tokens cannot be greater than input_audio_tokens");let w=0;if(t.cache_read_mtok!==void 0&&(w=r-u),w<0)throw new Error("cache_audio_read_tokens cannot be greater than cache_read_tokens");const y=t.cache_write_mtok===void 0?0:m;let b=0;if(t.input_mtok!==void 0&&(b=o-w-y-l-u),b<0)throw new Error("Uncached text input tokens cannot be negative");i+=d(t.input_mtok,b,"input_mtok",o),i+=d(t.cache_read_mtok,w,"cache_read_mtok",o),i+=d(t.cache_write_mtok,y,"cache_write_mtok",o),i+=d(t.input_audio_mtok,l,"input_audio_mtok",o),i+=d(t.cache_audio_read_mtok,u,"cache_audio_read_mtok",o);let f=0;if(t.output_mtok!==void 0&&(f=(e.output_tokens??0)-(t.output_audio_mtok===void 0?0:c)),f<0)throw new Error("output_audio_tokens cannot be greater than output_tokens");a+=d(t.output_mtok,f,"output_mtok",o),a+=d(t.output_audio_mtok,e.output_audio_tokens,"output_audio_mtok",o);let I=i+a;return t.requests_kcount!==void 0&&(I+=t.requests_kcount/1e3),{input_price:i,output_price:a,total_price:I}}function z(e,t){if(!Array.isArray(e.prices))return e.prices;for(let i=e.prices.length-1;i>=0;i--){const a=e.prices[i],o=a.constraint;if(o===void 0)return a.prices;if(o.type==="start_date"){if(t>=new Date(o.start_date))return a.prices}else{const r=t.toISOString().slice(11,19),m=o.start_time,n=o.end_time;if(n<m){if(r>=m||r<n)return a.prices}else if(r>=m&&r<n)return a.prices}}return e.prices[0].prices}function g(e,t){return"or"in e?e.or.some(i=>g(i,t)):"and"in e?e.and.every(i=>g(i,t)):"equals"in e?t.toLowerCase()===e.equals.toLowerCase():"starts_with"in e?t.toLowerCase().startsWith(e.starts_with.toLowerCase()):"ends_with"in e?t.toLowerCase().endsWith(e.ends_with.toLowerCase()):"contains"in e?t.toLowerCase().includes(e.contains.toLowerCase()):"regex"in e?new RegExp(e.regex).test(t):!1}function C(e,t){const i=t.toLowerCase().trim(),a=e.find(o=>o.id===i);return a||e.find(o=>o.provider_match&&g(o.provider_match,i))}function x(e,{modelId:t,providerApiUrl:i,providerId:a}){if(a){const o=C(e,a);if(o||a.toLowerCase()!=="litellm")return o}if(i)return e.find(o=>new RegExp(o.api_pattern).test(i));if(t)return e.find(o=>o.model_match&&g(o.model_match,t))}function R(e,t){return e.find(i=>g(i.match,t))}function P(e,t,i){const a=R(e.models,t);if(a)return a;if(e.fallback_model_providers&&i)for(const o of e.fallback_model_providers){const r=i.find(m=>m.id===o);if(r){const m=P(r,t);if(m)return m}}}const A="https://raw.githubusercontent.com/pydantic/genai-prices/main/prices/data.json";let k=G,B=Promise.resolve(G),M=null;function V(e){e!==null&&("then"in e?(B=e,e.then(t=>{t!==null&&(k=t)})):(B=Promise.resolve(e),k=e))}function D(e){M=e}function N(e){e({onCalc:D,remoteDataUrl:A,setProviderData:V})}function F(){return B}function E(e,t,i){M?.();let a=t.toLowerCase().trim(),o=i?.providerId;if(o&&o.toLowerCase()==="litellm"&&a.includes("/")){const u=a.indexOf("/"),p=a.slice(0,u),l=a.slice(u+1);p&&l&&x(k,{providerId:p})&&(o=p,a=l)}const r=i?.provider??x(k,{modelId:a,providerApiUrl:i?.providerApiUrl,providerId:o});if(!r)return null;const m=P(r,a,k);if(!m)return null;const n=i?.timestamp??new Date,s=z(m,n),c=S(e,s);return{auto_update_timestamp:void 0,model:m,model_price:s,provider:r,...c}}function O(e){return M?.(),x(k,e)}function K(e,t,i){if(i=i??"default",!e.extractors)throw new Error("No extraction logic defined for this provider");const a=e.extractors.find(s=>s.api_flavor===i);if(!a){const s=e.extractors.map(c=>c.api_flavor).join(", ");throw new Error(`Unknown apiFlavor '${i}', allowed values: ${s}`)}if(!q.guard(t))throw new Error(`Expected response data to be a mapping object, got ${_(t)}`);const o=v(a.model_path,t,H,!1,[]),r=Q(a.root),m=v(r,t,q,!0,[]),n={};for(const s of a.mappings){const c=v(s.path,m,U,s.required,r);if(c!==null){const u=n[s.dest]??0;n[s.dest]=u+c}}if(!Object.keys(n).length)throw new Error(`No usage information found at ${JSON.stringify(a.root)}`);return{model:o,usage:n}}function v(e,t,i,a,o){const[r,...m]=Q(e).reverse();if(typeof r!="string")throw new Error(`Expected last step of path to be a string, got ${_(r)}`);m.reverse();let n=t;const s=[];for(const u of m){if(s.push(u),typeof u=="object")if(Array.isArray(n))n=j(u,n);else{if(a)throw new Error(`Expected \`${h(o,s)}\` value to be a mapping, got ${_(n)}`);return null}else if(q.guard(n))n=n[u];else{if(a)throw new Error(`Expected \`${h(o,s)}\` value to be a mapping, got ${_(n)}`);return null}if(typeof n>"u")if(a){const p=typeof u=="object"?"Unable to find item":"Missing value";throw new Error(`${p} at \`${h(o,s)}\``)}else return null}if(!q.guard(n)){if(a)throw new Error(`Expected \`${h(o,s)}\` value to be a mapping, got ${_(n)}`);return null}const c=n[r];if(typeof c>"u"){if(a)throw s.push(r),new Error(`Missing value at \`${h(o,s)}\``);return null}if(i.guard(c))return c;if(a)throw s.push(r),new Error(`Expected \`${h(o,s)}\` value to be a ${i.name}, got ${_(c)}`);return null}function j(e,t){for(const i of t)if(q.guard(i)){const a=i[e.field];if(typeof a=="string"&&g(e.match,a))return i}}function Q(e){return Array.isArray(e)?[...e]:[e]}function _(e){return e===null?"null":Array.isArray(e)?"array":typeof e=="object"?"mapping":typeof e}const q={guard:e=>_(e)==="mapping",name:"mapping"},H={guard:e=>typeof e=="string",name:"string"},U={guard:e=>typeof e=="number",name:"number"},h=(e,t)=>[...e.map(L),...t.map(L)].join("."),L=e=>typeof e=="string"?e:JSON.stringify(e);class ${base;tiers;constructor(t){this.base=t.base,this.tiers=[...t.tiers].sort((i,a)=>i.start-a.start)}}exports.REMOTE_DATA_JSON_URL=A;exports.TieredPrices=$;exports.calcPrice=E;exports.extractUsage=K;exports.findProvider=O;exports.updatePrices=N;exports.waitForUpdate=F;