@agentjido/llmdb 2026.8.2 → 2026.8.3

package/dist/providers/abacus.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://routellm.abacus.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://abacus.ai/help/api","env":["ABACUS_API_KEY"],"exclude_models":null,"extra":null,"id":"abacus","models":{"MiniMaxAI/MiniMax-M2.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","llmfit":{"architecture":"minimax_m2","context_length":204800,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.7-GGUF"}],"hf_downloads":917214,"hf_likes":1236,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.7","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.7","moe":{"active_experts":8,"active_parameters":10000000000,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-04-09","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"MiniMaxAI/MiniMax-M3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","llmfit":{"architecture":"minimax_m3_vl","context_length":1048576,"discovered":false,"gguf_sources":[],"hf_downloads":164790,"hf_likes":1418,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M3","memory":{"min_ram_gb":238.6,"min_vram_gb":218.7,"recommended_ram_gb":397.7},"model_id":"MiniMaxAI/MiniMax-M3","moe":{"active_experts":4,"active_parameters":10000000000,"is_moe":true,"num_experts":128},"parameter_count":"427.0B","parameters_raw":427040140160,"pipeline_tag":"image-text-to-text","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-06-02","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"Qwen/QwQ-32B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","llmfit":{"architecture":"qwen2","context_length":40960,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/QwQ-32B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/QwQ-32B-GGUF"}],"hf_downloads":357800,"hf_likes":2958,"matched_hugging_face_id":"Qwen/QwQ-32B","memory":{"min_ram_gb":18.3,"min_vram_gb":16.8,"recommended_ram_gb":30.5},"model_id":"Qwen/QwQ-32B","parameter_count":"32.8B","parameters_raw":32763876352,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-03-05","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"Qwen/QwQ-32B","knowledge":null,"last_updated":"2024-11-28","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"QwQ 32B","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-11-28","retired":false,"tags":null},"Qwen/Qwen2.5-72B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.11,"output":0.38},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen2","context_length":32768,"discovered":false,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/Qwen2.5-72B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-72B-Instruct-GGUF"}],"hf_downloads":445760,"hf_likes":968,"matched_hugging_face_id":"Qwen/Qwen2.5-72B-Instruct","memory":{"min_ram_gb":40.6,"min_vram_gb":37.2,"recommended_ram_gb":67.7},"model_id":"Qwen/Qwen2.5-72B-Instruct","parameter_count":"72.7B","parameters_raw":72706203648,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2024-09-16","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"temperature":true},"family":null,"id":"Qwen/Qwen2.5-72B-Instruct","knowledge":null,"last_updated":"2024-09-19","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 2.5 72B Instruct","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-09-19","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B-Instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF"}],"hf_downloads":59827,"hf_likes":793,"matched_hugging_face_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","memory":{"min_ram_gb":131.4,"min_vram_gb":120.4,"recommended_ram_gb":218.9},"model_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","moe":{"active_experts":8,"active_parameters":25713366280,"is_moe":true,"num_experts":128},"parameter_count":"235.1B","parameters_raw":235093634560,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-21","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","knowledge":null,"last_updated":"2025-07-01","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Instruct","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-07-01","retired":false,"tags":null},"Qwen/Qwen3-32B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.09,"output":0.29},"deprecated":false,"extra":{"attachment":false,"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-32B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-32B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-32B-GGUF"}],"hf_downloads":8526764,"hf_likes":727,"matched_hugging_face_id":"Qwen/Qwen3-32B","memory":{"min_ram_gb":18.3,"min_vram_gb":16.8,"recommended_ram_gb":30.5},"model_id":"Qwen/Qwen3-32B","parameter_count":"32.8B","parameters_raw":32762123264,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"Qwen/Qwen3-32B","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"Qwen/Qwen3-Coder-480B-A35B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.29,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF"}],"hf_downloads":91304,"hf_likes":1357,"matched_hugging_face_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","memory":{"min_ram_gb":268.3,"min_vram_gb":245.9,"recommended_ram_gb":447.2},"model_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","moe":{"active_experts":8,"active_parameters":35000000000,"is_moe":true,"num_experts":160},"parameter_count":"480.2B","parameters_raw":480154875392,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-22","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder 480B-A35B Instruct","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"Qwen/Qwen3.6-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.32,"output":3.2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-27B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-27B-GGUF"}],"hf_downloads":6895121,"hf_likes":2145,"matched_hugging_face_id":"Qwen/Qwen3.6-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.6-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-21","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-27B","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"claude-3-7-sonnet-20250219":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-3-7-sonnet-20250219","knowledge":"2024-10-31","last_updated":"2025-02-19","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 3.7","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-02-19","retired":false,"tags":null},"claude-fable-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"claude-fable-5","knowledge":"2026-01-31","last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Fable 5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"claude-haiku-4-5-20251001":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-haiku-4-5-20251001","knowledge":"2025-02-28","last_updated":"2025-10-15","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Haiku 4.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"claude-opus-4-1-20250805":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-opus-4-1-20250805","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"claude-opus-4-20250514":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-opus-4-20250514","knowledge":null,"last_updated":"2025-05-14","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-05-14","retired":false,"tags":null},"claude-opus-4-5-20251101":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-opus-4-5-20251101","knowledge":"2025-05","last_updated":"2025-11-01","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-01","retired":false,"tags":null},"claude-opus-4-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-opus-4-6","knowledge":"2025-05-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.6","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"claude-opus-4-7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"claude-opus-4-7","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"claude-opus-4-8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"claude-opus-4-8","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"claude-sonnet-4-20250514":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-sonnet-4-20250514","knowledge":null,"last_updated":"2025-05-14","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-05-14","retired":false,"tags":null},"claude-sonnet-4-5-20250929":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-sonnet-4-5-20250929","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"claude-sonnet-4-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-sonnet-4-6","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"claude-sonnet-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"deepseek-ai/DeepSeek-R1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":7},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-R1-GGUF"}],"hf_downloads":9604023,"hf_likes":13537,"matched_hugging_face_id":"deepseek-ai/DeepSeek-R1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-R1","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-01-20","source":"llmfit","use_case":"Advanced reasoning, chain-of-thought"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-R1","knowledge":null,"last_updated":"2025-01-20","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.1-Terminus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":16978,"hf_likes":0,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.1-Terminus","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3.1-Terminus","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.1-Terminus","knowledge":null,"last_updated":"2025-06-01","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.1 Terminus","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-06-01","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v32","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-V3.2-GGUF"}],"hf_downloads":1238427,"hf_likes":1462,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.2","memory":{"min_ram_gb":383.0,"min_vram_gb":351.1,"recommended_ram_gb":638.3},"model_id":"deepseek-ai/DeepSeek-V3.2","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"685.4B","parameters_raw":685396921376,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-12-01","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2","knowledge":null,"last_updated":"2025-06-15","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-06-15","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":2746291,"hf_likes":1982,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","memory":{"min_ram_gb":162.6,"min_vram_gb":149.0,"recommended_ram_gb":271.0},"model_id":"deepseek-ai/DeepSeek-V4-Flash","moe":{"active_experts":6,"active_parameters":13000000000,"is_moe":true,"num_experts":256},"parameter_count":"290.9B","parameters_raw":290944616402,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.74,"output":3.48},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":1596582,"hf_likes":5373,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","memory":{"min_ram_gb":893.4,"min_vram_gb":819.0,"recommended_ram_gb":1489.0},"model_id":"deepseek-ai/DeepSeek-V4-Pro","moe":{"active_experts":6,"active_parameters":49000000000,"is_moe":true,"num_experts":384},"parameter_count":"1598.8B","parameters_raw":1598839674782,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek/deepseek-v3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.55,"output":1.66},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek/deepseek-v3.1","knowledge":null,"last_updated":"2025-01-20","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"gemini-2.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-flash","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-2.5-flash-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.3,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gemini-2.5-flash-image","knowledge":"2024-06","last_updated":"2025-08-26","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"gemini-2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-pro","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 2.5 Pro","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-3-flash-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-flash-preview","knowledge":"2025-01","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 3 Flash Preview","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"gemini-3-pro-image-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gemini-3-pro-image-preview","knowledge":"2025-01","last_updated":"2025-11-20","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana Pro","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-20","retired":false,"tags":null},"gemini-3.1-flash-image-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gemini-3.1-flash-image-preview","knowledge":"2025-01","last_updated":"2026-02-26","lifecycle":null,"limits":{"context":1048576,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana 2","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"gemini-3.1-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-flash-lite","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"gemini-3.1-flash-lite-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"cache_write":1,"input":0.25,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-flash-lite-preview","knowledge":null,"last_updated":"2026-03-01","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite Preview","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-01","retired":false,"tags":null},"gemini-3.1-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-pro-preview","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"gemini-3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"google/gemma-4-31b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"gpt-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-4.1","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.4,"output":1.6},"deprecated":false,"extra":{"attachment":true,"description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-4.1-mini","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1 mini","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.1,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-4.1-nano","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1 nano","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4o":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-4o","knowledge":"2023-09","last_updated":"2024-08-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"gpt-4o-2024-11-20":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"gpt-4o-2024-11-20","knowledge":"2024-10","last_updated":"2024-11-20","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"GPT-4o (2024-11-20)","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-11-20","retired":false,"tags":null},"gpt-4o-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-4o-mini","knowledge":"2023-09","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o mini","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"gpt-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5","knowledge":"2024-09-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-codex","knowledge":"2024-09-30","last_updated":"2025-09-15","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5-Codex","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-09-15","retired":false,"tags":null},"gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-mini","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Mini","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.005,"input":0.05,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-nano","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Nano","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"gpt-5.1-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"gpt-5.1-chat-latest","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Chat Latest","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"gpt-5.1-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1-codex","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"gpt-5.1-codex-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1-codex-max","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex Max","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"gpt-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.2","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"gpt-5.2-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gpt-5.2-chat-latest","knowledge":"2024-09-30","last_updated":"2026-01-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2 Chat Latest","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-01-01","retired":false,"tags":null},"gpt-5.2-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.2-codex","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2 Codex","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"gpt-5.3-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gpt-5.3-chat-latest","knowledge":null,"last_updated":"2026-03-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.3 Chat Latest","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-01","retired":false,"tags":null},"gpt-5.3-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.18,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.3-codex","knowledge":"2025-08-31","last_updated":"2026-02-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.3 Codex","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"gpt-5.3-codex-xhigh":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.3-codex-xhigh","knowledge":"2025-08-31","last_updated":"2026-02-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.3 Codex XHigh","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"gpt-5.4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"gpt-5.4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.75,"output":4.5},"deprecated":false,"extra":{"attachment":true,"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4-mini","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 mini","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"gpt-5.4-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.2,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4-nano","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 nano","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"gpt-5.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"gpt-5.6-luna":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":1,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.6-luna","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Luna","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5.6-sol":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.6-sol","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5.6-terra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.6-terra","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Terra","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"grok-4-0709":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"grok-4-0709","knowledge":null,"last_updated":"2025-07-09","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-07-09","retired":false,"tags":null},"grok-4-1-fast-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"grok-4-1-fast-non-reasoning","knowledge":null,"last_updated":"2025-11-17","lifecycle":null,"limits":{"context":2000000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.1 Fast (Non-Reasoning)","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-17","retired":false,"tags":null},"grok-4-fast-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"grok-4-fast-non-reasoning","knowledge":null,"last_updated":"2025-07-09","lifecycle":null,"limits":{"context":2000000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4 Fast (Non-Reasoning)","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-07-09","retired":false,"tags":null},"grok-4.3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"grok-4.3","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.3","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"grok-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"xAI's latest Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"grok-4.5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"grok-code-fast-1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"grok-code-fast-1","knowledge":null,"last_updated":"2025-09-01","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok Code Fast 1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-09-01","retired":false,"tags":null},"kimi-k2-turbo-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":8},"deprecated":false,"extra":{"attachment":false,"description":"Fast Kimi model for responsive chat, coding help, and agent loops","family":"kimi-k2","open_weights":false,"temperature":true},"family":null,"id":"kimi-k2-turbo-preview","knowledge":null,"last_updated":"2025-07-08","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Turbo Preview","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-07-08","retired":false,"tags":null},"kimi-k2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2.5","knowledge":"2025-01","last_updated":"2026-01","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"llama-3.3-70b-versatile":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.59,"output":0.79},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama-3.3-70b-versatile","knowledge":null,"last_updated":"2024-12-06","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Versatile","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.59},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","llmfit":{"architecture":"llama4","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":117872,"hf_likes":0,"matched_hugging_face_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","memory":{"min_ram_gb":224.4,"min_vram_gb":205.7,"recommended_ram_gb":374.1},"model_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","moe":{"active_experts":1,"active_parameters":43930451431,"is_moe":true,"num_experts":16},"parameter_count":"401.6B","parameters_raw":401649841664,"pipeline_tag":"image-text-to-text","provider":"Meta","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"temperature":true},"family":null,"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","knowledge":"2024-08","last_updated":"2025-04-05","lifecycle":null,"limits":{"context":1048576,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Maverick 17B Instruct","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3.5,"output":3.5},"deprecated":false,"extra":{"attachment":false,"description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo","knowledge":null,"last_updated":"2024-07-23","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 405B Instruct Turbo","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"meta-llama/Meta-Llama-3.1-8B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.02,"output":0.05},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"meta-llama/Meta-Llama-3.1-8B-Instruct","knowledge":null,"last_updated":"2024-07-23","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B Instruct","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"meta-llama/Meta-Llama-3.3-70B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.59,"output":0.79},"deprecated":false,"extra":{"attachment":true,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"meta-llama/Meta-Llama-3.3-70B-Instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"mimo-v2-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"mimo-v2-pro","knowledge":"2024-12","last_updated":"2026-03-18","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2-Pro","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.19,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"muse-spark-1.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"deprecated":false,"extra":{"attachment":true,"description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"muse-spark-1.1","knowledge":null,"last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":32000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Muse Spark 1.1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-08","retired":false,"tags":null},"o3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"o3","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o3","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"o3-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"o3-mini","knowledge":"2024-05","last_updated":"2025-01-29","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"o3-mini","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-12-20","retired":false,"tags":null},"o3-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":20,"output":40},"deprecated":false,"extra":{"attachment":true,"description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"o3-pro","knowledge":"2024-05","last_updated":"2025-06-10","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o3-pro","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-06-10","retired":false,"tags":null},"o4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"o4-mini","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o4-mini","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.08,"output":0.44},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"qwen-2.5-coder-32b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.79,"output":0.79},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen-2.5-coder-32b","knowledge":null,"last_updated":"2024-11-11","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 2.5 Coder 32B","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-11-11","retired":false,"tags":null},"qwen3-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3-max","knowledge":null,"last_updated":"2025-05-28","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Max","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-05-28","retired":false,"tags":null},"route-llm":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"RouteLLM routes prompts to an appropriate Abacus-backed text-generation model","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"route-llm","knowledge":null,"last_updated":"2026-07-10","lifecycle":null,"limits":{"context":128000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"RouteLLM","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"zai-org/GLM-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","llmfit":{"architecture":"glm4_moe","context_length":131072,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.5-GGUF"}],"hf_downloads":123213,"hf_likes":1408,"matched_hugging_face_id":"zai-org/GLM-4.5","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.5","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-07-20","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-4.5","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":131072,"output":96000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"zai-org/GLM-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.6-GGUF"}],"hf_downloads":26467,"hf_likes":1229,"matched_hugging_face_id":"zai-org/GLM-4.6","memory":{"min_ram_gb":199.4,"min_vram_gb":182.8,"recommended_ram_gb":332.3},"model_id":"zai-org/GLM-4.6","moe":{"active_experts":8,"active_parameters":34786625132,"is_moe":true,"num_experts":160},"parameter_count":"356.8B","parameters_raw":356785898816,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-09-29","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-4.6","knowledge":"2025-04","last_updated":"2025-09-30","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.6","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"zai-org/GLM-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.7-GGUF"}],"hf_downloads":72466,"hf_likes":2051,"matched_hugging_face_id":"zai-org/GLM-4.7","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.7","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-12-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"zai-org/GLM-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5-GGUF"}],"hf_downloads":155600,"hf_likes":2119,"matched_hugging_face_id":"zai-org/GLM-5","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5","moe":{"active_experts":8,"active_parameters":40000000000,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-02-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"zai-org/GLM-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5.1-GGUF"}],"hf_downloads":76699,"hf_likes":1840,"matched_hugging_face_id":"zai-org/GLM-5.1","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1","moe":{"active_experts":8,"active_parameters":60073548574,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","llmfit":{"architecture":"glm_moe_dsa","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2180509,"hf_likes":4785,"matched_hugging_face_id":"zai-org/GLM-5.2","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2","moe":{"active_experts":8,"active_parameters":60030979632,"is_moe":true,"num_experts":256},"parameter_count":"753.3B","parameters_raw":753329940480,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-06-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Abacus","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://routellm.abacus.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://abacus.ai/help/api","env":["ABACUS_API_KEY"],"exclude_models":null,"extra":null,"id":"abacus","models":{"MiniMaxAI/MiniMax-M2.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","llmfit":{"architecture":"minimax_m2","context_length":204800,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.7-GGUF"}],"hf_downloads":896905,"hf_likes":1240,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.7","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.7","moe":{"active_experts":8,"active_parameters":10000000000,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228689764864,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-04-09","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"MiniMaxAI/MiniMax-M3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","llmfit":{"architecture":"minimax_m3_vl","context_length":1048576,"discovered":false,"gguf_sources":[],"hf_downloads":170183,"hf_likes":1473,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M3","memory":{"min_ram_gb":238.6,"min_vram_gb":218.7,"recommended_ram_gb":397.7},"model_id":"MiniMaxAI/MiniMax-M3","moe":{"active_experts":4,"active_parameters":10000000000,"is_moe":true,"num_experts":128},"parameter_count":"427.0B","parameters_raw":427040140160,"pipeline_tag":"image-text-to-text","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-06-02","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"Qwen/QwQ-32B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","llmfit":{"architecture":"qwen2","context_length":40960,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/QwQ-32B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/QwQ-32B-GGUF"}],"hf_downloads":87389,"hf_likes":2962,"matched_hugging_face_id":"Qwen/QwQ-32B","memory":{"min_ram_gb":18.3,"min_vram_gb":16.8,"recommended_ram_gb":30.5},"model_id":"Qwen/QwQ-32B","parameter_count":"32.8B","parameters_raw":32763876352,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-03-05","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"Qwen/QwQ-32B","knowledge":null,"last_updated":"2024-11-28","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"QwQ 32B","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-11-28","retired":false,"tags":null},"Qwen/Qwen2.5-72B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.11,"output":0.38},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen2","context_length":32768,"discovered":false,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/Qwen2.5-72B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-72B-Instruct-GGUF"}],"hf_downloads":374955,"hf_likes":972,"matched_hugging_face_id":"Qwen/Qwen2.5-72B-Instruct","memory":{"min_ram_gb":40.6,"min_vram_gb":37.2,"recommended_ram_gb":67.7},"model_id":"Qwen/Qwen2.5-72B-Instruct","parameter_count":"72.7B","parameters_raw":72706203648,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2024-09-16","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"temperature":true},"family":null,"id":"Qwen/Qwen2.5-72B-Instruct","knowledge":null,"last_updated":"2024-09-19","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 2.5 72B Instruct","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-09-19","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B-Instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF"}],"hf_downloads":48827,"hf_likes":793,"matched_hugging_face_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","memory":{"min_ram_gb":131.4,"min_vram_gb":120.4,"recommended_ram_gb":218.9},"model_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","moe":{"active_experts":8,"active_parameters":25713366280,"is_moe":true,"num_experts":128},"parameter_count":"235.1B","parameters_raw":235093634560,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-21","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","knowledge":null,"last_updated":"2025-07-01","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Instruct","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-07-01","retired":false,"tags":null},"Qwen/Qwen3-32B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.09,"output":0.29},"deprecated":false,"extra":{"attachment":false,"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-32B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-32B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-32B-GGUF"}],"hf_downloads":6915474,"hf_likes":732,"matched_hugging_face_id":"Qwen/Qwen3-32B","memory":{"min_ram_gb":18.3,"min_vram_gb":16.8,"recommended_ram_gb":30.5},"model_id":"Qwen/Qwen3-32B","parameter_count":"32.8B","parameters_raw":32762123264,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"Qwen/Qwen3-32B","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"Qwen/Qwen3-Coder-480B-A35B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.29,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF"}],"hf_downloads":91107,"hf_likes":1360,"matched_hugging_face_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","memory":{"min_ram_gb":268.3,"min_vram_gb":245.9,"recommended_ram_gb":447.2},"model_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","moe":{"active_experts":8,"active_parameters":35000000000,"is_moe":true,"num_experts":160},"parameter_count":"480.2B","parameters_raw":480154875392,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-22","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder 480B-A35B Instruct","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"Qwen/Qwen3.6-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.32,"output":3.2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-27B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-27B-GGUF"}],"hf_downloads":6928584,"hf_likes":2266,"matched_hugging_face_id":"Qwen/Qwen3.6-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.6-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-21","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-27B","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"claude-3-7-sonnet-20250219":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-3-7-sonnet-20250219","knowledge":"2024-10-31","last_updated":"2025-02-19","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 3.7","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-02-19","retired":false,"tags":null},"claude-fable-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"claude-fable-5","knowledge":"2026-01-31","last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Fable 5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"claude-haiku-4-5-20251001":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-haiku-4-5-20251001","knowledge":"2025-02-28","last_updated":"2025-10-15","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Haiku 4.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"claude-opus-4-1-20250805":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-opus-4-1-20250805","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"claude-opus-4-20250514":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-opus-4-20250514","knowledge":null,"last_updated":"2025-05-14","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-05-14","retired":false,"tags":null},"claude-opus-4-5-20251101":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-opus-4-5-20251101","knowledge":"2025-05","last_updated":"2025-11-01","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-01","retired":false,"tags":null},"claude-opus-4-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-opus-4-6","knowledge":"2025-05-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.6","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"claude-opus-4-7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"claude-opus-4-7","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"claude-opus-4-8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"claude-opus-4-8","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"claude-opus-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"claude-opus-5","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"claude-sonnet-4-20250514":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-sonnet-4-20250514","knowledge":null,"last_updated":"2025-05-14","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-05-14","retired":false,"tags":null},"claude-sonnet-4-5-20250929":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-sonnet-4-5-20250929","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"claude-sonnet-4-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-sonnet-4-6","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"claude-sonnet-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"deepseek-ai/DeepSeek-R1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":7},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-R1-GGUF"}],"hf_downloads":7455596,"hf_likes":13576,"matched_hugging_face_id":"deepseek-ai/DeepSeek-R1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-R1","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-01-20","source":"llmfit","use_case":"Advanced reasoning, chain-of-thought"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-R1","knowledge":null,"last_updated":"2025-01-20","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.1-Terminus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":19456,"hf_likes":0,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.1-Terminus","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3.1-Terminus","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.1-Terminus","knowledge":null,"last_updated":"2025-06-01","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.1 Terminus","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-06-01","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v32","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-V3.2-GGUF"}],"hf_downloads":1173317,"hf_likes":1467,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.2","memory":{"min_ram_gb":383.0,"min_vram_gb":351.1,"recommended_ram_gb":638.3},"model_id":"deepseek-ai/DeepSeek-V3.2","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"685.4B","parameters_raw":685396921376,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-12-01","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2","knowledge":null,"last_updated":"2025-06-15","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-06-15","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":2045206,"hf_likes":2109,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","memory":{"min_ram_gb":162.6,"min_vram_gb":149.0,"recommended_ram_gb":271.0},"model_id":"deepseek-ai/DeepSeek-V4-Flash","moe":{"active_experts":6,"active_parameters":13000000000,"is_moe":true,"num_experts":256},"parameter_count":"290.9B","parameters_raw":290944616402,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.74,"output":3.48},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":1278742,"hf_likes":5452,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","memory":{"min_ram_gb":893.4,"min_vram_gb":819.0,"recommended_ram_gb":1489.0},"model_id":"deepseek-ai/DeepSeek-V4-Pro","moe":{"active_experts":6,"active_parameters":49000000000,"is_moe":true,"num_experts":384},"parameter_count":"1598.8B","parameters_raw":1598839674782,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek/deepseek-v3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.55,"output":1.66},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek/deepseek-v3.1","knowledge":null,"last_updated":"2025-01-20","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"gemini-2.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-flash","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-2.5-flash-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.3,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gemini-2.5-flash-image","knowledge":"2024-06","last_updated":"2025-08-26","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"gemini-2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-pro","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 2.5 Pro","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-3-flash-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-flash-preview","knowledge":"2025-01","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 3 Flash Preview","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"gemini-3-pro-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gemini-3-pro-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana Pro","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"gemini-3-pro-image-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gemini-3-pro-image-preview","knowledge":"2025-01","last_updated":"2025-11-20","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana Pro","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-20","retired":false,"tags":null},"gemini-3.1-flash-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gemini-3.1-flash-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1048576,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana 2","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"gemini-3.1-flash-image-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gemini-3.1-flash-image-preview","knowledge":"2025-01","last_updated":"2026-02-26","lifecycle":null,"limits":{"context":1048576,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana 2","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"gemini-3.1-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-flash-lite","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"gemini-3.1-flash-lite-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"cache_write":1,"input":0.25,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-flash-lite-preview","knowledge":null,"last_updated":"2026-03-01","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite Preview","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-01","retired":false,"tags":null},"gemini-3.1-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-pro-preview","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"gemini-3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"gemini-3.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash-lite","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash Lite","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"gemini-3.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"output":7.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.6-flash","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"gemini-3.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"deprecated":false,"extra":{"attachment":true,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.7-flash","knowledge":"2026-03","last_updated":"2026-08-13","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Gemini 3.7 Flash","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-08-13","retired":false,"tags":null},"google/gemma-4-31b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"gpt-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-4.1","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.4,"output":1.6},"deprecated":false,"extra":{"attachment":true,"description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-4.1-mini","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1 mini","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.1,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-4.1-nano","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1 nano","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4o":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-4o","knowledge":"2023-09","last_updated":"2024-08-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"gpt-4o-2024-11-20":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"gpt-4o-2024-11-20","knowledge":"2024-10","last_updated":"2024-11-20","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"GPT-4o (2024-11-20)","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-11-20","retired":false,"tags":null},"gpt-4o-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-4o-mini","knowledge":"2023-09","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o mini","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"gpt-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5","knowledge":"2024-09-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-codex","knowledge":"2024-09-30","last_updated":"2025-09-15","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5-Codex","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-09-15","retired":false,"tags":null},"gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-mini","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Mini","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.005,"input":0.05,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-nano","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Nano","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"gpt-5.1-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"gpt-5.1-chat-latest","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Chat Latest","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"gpt-5.1-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1-codex","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"gpt-5.1-codex-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1-codex-max","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex Max","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"gpt-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.2","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"gpt-5.2-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gpt-5.2-chat-latest","knowledge":"2024-09-30","last_updated":"2026-01-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2 Chat Latest","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-01-01","retired":false,"tags":null},"gpt-5.2-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.2-codex","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2 Codex","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"gpt-5.3-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gpt-5.3-chat-latest","knowledge":null,"last_updated":"2026-03-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.3 Chat Latest","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-01","retired":false,"tags":null},"gpt-5.3-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.18,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.3-codex","knowledge":"2025-08-31","last_updated":"2026-02-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.3 Codex","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"gpt-5.3-codex-xhigh":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.3-codex-xhigh","knowledge":"2025-08-31","last_updated":"2026-02-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.3 Codex XHigh","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"gpt-5.4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"gpt-5.4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.75,"output":4.5},"deprecated":false,"extra":{"attachment":true,"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4-mini","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 mini","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"gpt-5.4-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.2,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4-nano","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 nano","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"gpt-5.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"gpt-5.6-luna":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":1,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.6-luna","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Luna","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5.6-sol":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.6-sol","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5.6-terra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.6-terra","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Terra","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"grok-4-0709":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"grok-4-0709","knowledge":null,"last_updated":"2025-07-09","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-07-09","retired":false,"tags":null},"grok-4-1-fast-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"grok-4-1-fast-non-reasoning","knowledge":null,"last_updated":"2025-11-17","lifecycle":null,"limits":{"context":2000000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.1 Fast (Non-Reasoning)","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-11-17","retired":false,"tags":null},"grok-4-fast-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"grok-4-fast-non-reasoning","knowledge":null,"last_updated":"2025-07-09","lifecycle":null,"limits":{"context":2000000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4 Fast (Non-Reasoning)","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-07-09","retired":false,"tags":null},"grok-4.3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"grok-4.3","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.3","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"grok-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"grok-4.5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"grok-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"grok-4.6","knowledge":"2026-02-01","last_updated":"2026-08-12","lifecycle":null,"limits":{"context":500000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.6","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"grok-code-fast-1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"grok-code-fast-1","knowledge":null,"last_updated":"2025-09-01","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok Code Fast 1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-09-01","retired":false,"tags":null},"kimi-k2-turbo-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":8},"deprecated":false,"extra":{"attachment":false,"description":"Fast Kimi model for responsive chat, coding help, and agent loops","family":"kimi-k2","open_weights":false,"temperature":true},"family":null,"id":"kimi-k2-turbo-preview","knowledge":null,"last_updated":"2025-07-08","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Turbo Preview","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-07-08","retired":false,"tags":null},"kimi-k2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2.5","knowledge":"2025-01","last_updated":"2026-01","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"llama-3.3-70b-versatile":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.59,"output":0.79},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama-3.3-70b-versatile","knowledge":null,"last_updated":"2024-12-06","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Versatile","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.59},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","llmfit":{"architecture":"llama4","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":107564,"hf_likes":0,"matched_hugging_face_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","memory":{"min_ram_gb":224.4,"min_vram_gb":205.7,"recommended_ram_gb":374.1},"model_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","moe":{"active_experts":1,"active_parameters":43930451431,"is_moe":true,"num_experts":16},"parameter_count":"401.6B","parameters_raw":401649841664,"pipeline_tag":"image-text-to-text","provider":"Meta","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"temperature":true},"family":null,"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","knowledge":"2024-08","last_updated":"2025-04-05","lifecycle":null,"limits":{"context":1048576,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Maverick 17B Instruct","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3.5,"output":3.5},"deprecated":false,"extra":{"attachment":false,"description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo","knowledge":null,"last_updated":"2024-07-23","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 405B Instruct Turbo","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"meta-llama/Meta-Llama-3.1-8B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.02,"output":0.05},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"meta-llama/Meta-Llama-3.1-8B-Instruct","knowledge":null,"last_updated":"2024-07-23","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B Instruct","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"meta-llama/Meta-Llama-3.3-70B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.59,"output":0.79},"deprecated":false,"extra":{"attachment":true,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"meta-llama/Meta-Llama-3.3-70B-Instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"mimo-v2-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"mimo-v2-pro","knowledge":"2024-12","last_updated":"2026-03-18","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2-Pro","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.19,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":805859,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":71667623138,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K2.7-Code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.19,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":568317,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":71667623138,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/Kimi-K2.7-Code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshotai/Kimi-K3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","llmfit":{"architecture":"kimi_k3","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2136775,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K3","memory":{"min_ram_gb":1553.4,"min_vram_gb":1424.0,"recommended_ram_gb":2589.0},"model_id":"moonshotai/Kimi-K3","parameter_count":"2779.9B","parameters_raw":2779931837184,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/Kimi-K3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"muse-spark-1.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"deprecated":false,"extra":{"attachment":true,"description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"muse-spark-1.1","knowledge":null,"last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":32000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Muse Spark 1.1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-08","retired":false,"tags":null},"muse-spark-1.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"deprecated":false,"extra":{"attachment":true,"description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"muse-spark-1.2","knowledge":null,"last_updated":"2026-08-05","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Muse Spark 1.2","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-08-05","retired":false,"tags":null},"o3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"o3","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o3","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"o3-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"o3-mini","knowledge":"2024-05","last_updated":"2025-01-29","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"o3-mini","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-12-20","retired":false,"tags":null},"o3-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":20,"output":40},"deprecated":false,"extra":{"attachment":true,"description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"o3-pro","knowledge":"2024-05","last_updated":"2025-06-10","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o3-pro","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-06-10","retired":false,"tags":null},"o4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"o4-mini","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o4-mini","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.08,"output":0.44},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4479205,"hf_likes":5106,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":65.3,"min_vram_gb":59.8,"recommended_ram_gb":108.8},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9309823421,"is_moe":true,"num_experts":128},"parameter_count":"116.8B","parameters_raw":116829156672,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"qwen-2.5-coder-32b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.79,"output":0.79},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen-2.5-coder-32b","knowledge":null,"last_updated":"2024-11-11","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 2.5 Coder 32B","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-11-11","retired":false,"tags":null},"qwen3-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3-max","knowledge":null,"last_updated":"2025-05-28","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Max","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-05-28","retired":false,"tags":null},"qwen3.7-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2.5,"output":7.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.7-max","knowledge":null,"last_updated":"2026-05-21","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.7 Max","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-05-21","retired":false,"tags":null},"qwen3.8-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.8-max","knowledge":null,"last_updated":"2026-08-03","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.8 Max","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-08-03","retired":false,"tags":null},"route-llm":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"RouteLLM routes prompts to an appropriate Abacus-backed text-generation model","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"route-llm","knowledge":null,"last_updated":"2026-07-10","lifecycle":null,"limits":{"context":128000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"RouteLLM","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"thinkingmachines/Inkling":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.748,"input":3.74,"output":9.36},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","llmfit":{"architecture":"inkling_mm_model","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":110771,"hf_likes":0,"matched_hugging_face_id":"thinkingmachines/Inkling","memory":{"min_ram_gb":532.2,"min_vram_gb":487.8,"recommended_ram_gb":887.0},"model_id":"thinkingmachines/Inkling","moe":{"active_experts":6,"active_parameters":68824164203,"is_moe":true,"num_experts":256},"parameter_count":"952.4B","parameters_raw":952377623626,"pipeline_tag":"image-text-to-text","provider":"thinkingmachines","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"thinkingmachines/Inkling","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"zai-org/GLM-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","llmfit":{"architecture":"glm4_moe","context_length":131072,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.5-GGUF"}],"hf_downloads":122008,"hf_likes":1408,"matched_hugging_face_id":"zai-org/GLM-4.5","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.5","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-07-20","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-4.5","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":131072,"output":96000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"zai-org/GLM-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.6-GGUF"}],"hf_downloads":27961,"hf_likes":1231,"matched_hugging_face_id":"zai-org/GLM-4.6","memory":{"min_ram_gb":199.4,"min_vram_gb":182.8,"recommended_ram_gb":332.3},"model_id":"zai-org/GLM-4.6","moe":{"active_experts":8,"active_parameters":34786625132,"is_moe":true,"num_experts":160},"parameter_count":"356.8B","parameters_raw":356785898816,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-09-29","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-4.6","knowledge":"2025-04","last_updated":"2025-09-30","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.6","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"zai-org/GLM-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.7-GGUF"}],"hf_downloads":71289,"hf_likes":2054,"matched_hugging_face_id":"zai-org/GLM-4.7","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.7","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-12-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"zai-org/GLM-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5-GGUF"}],"hf_downloads":124645,"hf_likes":2122,"matched_hugging_face_id":"zai-org/GLM-5","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5","moe":{"active_experts":8,"active_parameters":40000000000,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-02-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"zai-org/GLM-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5.1-GGUF"}],"hf_downloads":78747,"hf_likes":1840,"matched_hugging_face_id":"zai-org/GLM-5.1","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1","moe":{"active_experts":8,"active_parameters":60073548574,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","llmfit":{"architecture":"glm_moe_dsa","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2705686,"hf_likes":4983,"matched_hugging_face_id":"zai-org/GLM-5.2","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2","moe":{"active_experts":8,"active_parameters":60030979632,"is_moe":true,"num_experts":256},"parameter_count":"753.3B","parameters_raw":753329940480,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-06-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"abacus","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Abacus","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;