@agentjido/llmdb 2026.8.2

package/dist/providers/chutes.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://llm.chutes.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://llm.chutes.ai/v1/models","env":["CHUTES_API_KEY"],"exclude_models":null,"extra":null,"id":"chutes","models":{"Nemotron-3-Nano-Omni-30B-TEE":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.0024499999999999995,"input":0.0245,"output":0.0978},"deprecated":false,"extra":{"attachment":false,"description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"nemotron","open_weights":true,"temperature":true},"family":null,"id":"Nemotron-3-Nano-Omni-30B-TEE","knowledge":null,"last_updated":"2026-07-23","lifecycle":null,"limits":{"context":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano Omni 30B TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B-Thinking-2507-TEE":{"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":0.029889999999999993,"input":0.2989,"output":1.1957},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Thinking-2507-TEE","knowledge":"2025-04","last_updated":"2026-06-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Thinking 2507 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2025-07","retired":false,"tags":null},"Qwen/Qwen3-32B-TEE":{"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":0.010399999999999998,"input":0.104,"output":0.416},"deprecated":false,"extra":{"attachment":false,"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-32B-TEE","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":40960,"output":40960},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"Qwen/Qwen3.5-397B-A17B-TEE":{"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":0.04499999999999999,"input":0.45,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B-TEE","knowledge":null,"last_updated":"2026-02-15","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5 397B A17B TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"Qwen/Qwen3.6-27B-TEE":{"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":0.029999999999999992,"input":0.3,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-27B-TEE","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 27B TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2-TEE":{"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":0.09999999999999998,"input":1,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2-TEE","knowledge":null,"last_updated":"2026-06-21","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2025-12","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash-0731-TEE":{"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":0.013999999999999999,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash-0731-TEE","knowledge":"2025-05","last_updated":"2026-08-02","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"google/gemma-4-31B-turbo-TEE":{"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":0.011999999999999997,"input":0.12,"output":0.37},"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":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-turbo-TEE","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gemma 4 31B turbo TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"moonshotai/Kimi-K2.6-TEE":{"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":0.05799999999999998,"input":0.58,"output":3.4},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6-TEE","knowledge":"2025-12","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":65535},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K3-TEE":{"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":0.29999999999999993,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K3-TEE","knowledge":null,"last_updated":"2026-07-29","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-07-29","retired":false,"tags":null},"unsloth/Mistral-Nemo-Instruct-2407-TEE":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.0024499999999999995,"input":0.0245,"output":0.0978},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","open_weights":true,"temperature":true},"family":null,"id":"unsloth/Mistral-Nemo-Instruct-2407-TEE","knowledge":"2024-07","last_updated":"2024-07-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Nemo Instruct 2407 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2024-07-01","retired":false,"tags":null},"zai-org/GLM-5.1-TEE":{"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":0.09799999999999998,"input":0.98,"output":3.08},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1-TEE","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202752,"output":65535},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org/GLM-5.2-TEE":{"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":0.12499999999999997,"input":1.25,"output":3.95},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2-TEE","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Chutes","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/clarifai.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "clarifai",
+  "arcee_ai/AFM/models/trinity-mini" | "clarifai/main/models/mm-poly-8b" | "deepseek-ai/deepseek-ocr/models/DeepSeek-OCR" | "minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput" | "mistralai/completion/models/Ministral-3-14B-Reasoning-2512" | "mistralai/completion/models/Ministral-3-3B-Reasoning-2512" | "moonshotai/chat-completion/models/Kimi-K2_6" | "openai/chat-completion/models/gpt-oss-120b-high-throughput" | "openai/chat-completion/models/gpt-oss-20b" | "qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct" | "qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507" | "qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507"
+>;
+export default provider;

package/dist/providers/clarifai.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.clarifai.com/v2/ext/openai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.clarifai.com/compute/inference/","env":["CLARIFAI_PAT"],"exclude_models":null,"extra":null,"id":"clarifai","models":{"arcee_ai/AFM/models/trinity-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":0.045,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"trinity-mini","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"arcee_ai/AFM/models/trinity-mini","knowledge":"2024-10","last_updated":"2026-02-25","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Trinity Mini","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-12","retired":false,"tags":null},"clarifai/main/models/mm-poly-8b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.658,"output":1.11},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"mm-poly","open_weights":false,"temperature":true},"family":null,"id":"clarifai/main/models/mm-poly-8b","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":32768,"output":4096},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MM Poly 8B","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-06","retired":false,"tags":null},"deepseek-ai/deepseek-ocr/models/DeepSeek-OCR":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.2,"output":0.7},"deprecated":false,"extra":{"attachment":true,"description":"OCR model for extracting structured text from documents and screenshots","family":"deepseek","open_weights":true,"temperature":true},"family":null,"id":"deepseek-ai/deepseek-ocr/models/DeepSeek-OCR","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"DeepSeek OCR","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-10-20","retired":false,"tags":null},"minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput":{"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":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5 High Throughput","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"mistralai/completion/models/Ministral-3-14B-Reasoning-2512":{"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":1.7},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mistralai/completion/models/Ministral-3-14B-Reasoning-2512","knowledge":"2025-12","last_updated":"2025-12-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ministral 3 14B Reasoning 2512","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"mistralai/completion/models/Ministral-3-3B-Reasoning-2512":{"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":1.039,"output":0.54825},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mistralai/completion/models/Ministral-3-3B-Reasoning-2512","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ministral 3 3B Reasoning 2512","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-12","retired":false,"tags":null},"moonshotai/chat-completion/models/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":{"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","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/chat-completion/models/Kimi-K2_6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"openai/chat-completion/models/gpt-oss-120b-high-throughput":{"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":0.36},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/chat-completion/models/gpt-oss-120b-high-throughput","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B High Throughput","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/chat-completion/models/gpt-oss-20b":{"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":0.045,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/chat-completion/models/gpt-oss-20b","knowledge":null,"last_updated":"2025-12-12","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-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":0.11458,"output":0.74812},"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/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct","knowledge":"2025-04","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder 30B A3B Instruct","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-07-31","retired":false,"tags":null},"qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507":{"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":0.3,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B Instruct 2507","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-07-30","retired":false,"tags":null},"qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-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":0.36,"output":1.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B Thinking 2507","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-07-31","retired":false,"tags":null}},"name":"Clarifai","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/claudinio.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "claudinio",
+  "claudinio" | "claudius"
+>;
+export default provider;

package/dist/providers/claudinio.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.claudin.io/v1","catalog_only":true,"config_schema":null,"doc":"https://claudin.io","env":["CLAUDINIO_API_KEY"],"exclude_models":null,"extra":null,"id":"claudinio","models":{"claudinio":{"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":0.5,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","open_weights":false,"reasoning_options":[]},"family":null,"id":"claudinio","knowledge":"2026-05","last_updated":"2026-06-02","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Claudinio","pricing":null,"provider":"claudinio","provider_model_id":null,"release_date":"2026-05-12","retired":false,"tags":null},"claudius":{"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":0.9,"input":3,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","open_weights":false,"reasoning_options":[]},"family":null,"id":"claudius","knowledge":"2026-05","last_updated":"2026-05-12","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Claudius","pricing":null,"provider":"claudinio","provider_model_id":null,"release_date":"2026-05-12","retired":false,"tags":null}},"name":"Claudinio","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/cline_pass.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "cline_pass",
+  "cline-pass/deepseek-v4-flash" | "cline-pass/deepseek-v4-pro" | "cline-pass/glm-5.2" | "cline-pass/kimi-k2.6" | "cline-pass/kimi-k2.7-code" | "cline-pass/kimi-k3" | "cline-pass/mimo-v2.5" | "cline-pass/mimo-v2.5-pro" | "cline-pass/minimax-m3" | "cline-pass/qwen3.7-max" | "cline-pass/qwen3.7-plus"
+>;
+export default provider;

package/dist/providers/cline_pass.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.cline.bot/api/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.cline.bot/getting-started/clinepass","env":["CLINE_API_KEY"],"exclude_models":null,"extra":null,"id":"cline_pass","models":{"cline-pass/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":0.0028,"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","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"cline-pass/deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"cline_pass","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"cline-pass/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":0.0145,"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","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"cline-pass/deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"cline_pass","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"cline-pass/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","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"cline-pass/glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"cline_pass","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"cline-pass/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":0.16,"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","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"cline-pass/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":"cline_pass","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"cline-pass/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","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"cline-pass/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":"cline_pass","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"cline-pass/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","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"cline-pass/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":"cline_pass","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"cline-pass/mimo-v2.5":{"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":0.0028,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":true,"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"cline-pass/mimo-v2.5","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"MiMo-V2.5","pricing":null,"provider":"cline_pass","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"cline-pass/mimo-v2.5-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":0.0145,"input":1.74,"output":3.48},"deprecated":false,"extra":{"attachment":false,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"cline-pass/mimo-v2.5-pro","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2.5-Pro","pricing":null,"provider":"cline_pass","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"cline-pass/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":{"cache_read":0.06,"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","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"cline-pass/minimax-m3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":512000,"output":128000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"cline_pass","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"cline-pass/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":{"cache_read":0.5,"cache_write":3.125,"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":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"cline-pass/qwen3.7-max","knowledge":null,"last_updated":"2026-05-21","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.7 Max","pricing":null,"provider":"cline_pass","provider_model_id":null,"release_date":"2026-05-21","retired":false,"tags":null},"cline-pass/qwen3.7-plus":{"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":0.04,"cache_write":0.5,"input":0.4,"output":1.6},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"cline-pass/qwen3.7-plus","knowledge":"2025-04","last_updated":"2026-06-02","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.7 Plus","pricing":null,"provider":"cline_pass","provider_model_id":null,"release_date":"2026-06-02","retired":false,"tags":null}},"name":"ClinePass","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/cloudferro_sherlock.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "cloudferro_sherlock",
+  "MiniMaxAI/MiniMax-M2.5" | "meta-llama/Llama-3.3-70B-Instruct" | "openai/gpt-oss-120b" | "speakleash/Bielik-11B-v2.6-Instruct" | "speakleash/Bielik-11B-v3.0-Instruct"
+>;
+export default provider;

package/dist/providers/cloudferro_sherlock.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api-sherlock.cloudferro.com/openai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.sherlock.cloudferro.com/","env":["CLOUDFERRO_SHERLOCK_API_KEY"],"exclude_models":null,"extra":null,"id":"cloudferro_sherlock","models":{"MiniMaxAI/MiniMax-M2.5":{"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":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.5-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.5-GGUF"}],"hf_downloads":772099,"hf_likes":1502,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.5","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.5","moe":{"active_experts":8,"active_parameters":18224821702,"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":"2026-02-12","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5","knowledge":"2026-01","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":196000,"output":16000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5","pricing":null,"provider":"cloudferro_sherlock","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"meta-llama/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":2.92,"output":2.92},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","llmfit":{"architecture":"llama","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-3.3-70B-Instruct-GGUF"},{"provider":"bartowski","repo":"bartowski/Llama-3.3-70B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Llama-3.3-70B-Instruct-GGUF"}],"hf_downloads":478538,"hf_likes":2936,"matched_hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"meta-llama/Llama-3.3-70B-Instruct","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-11-26","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"temperature":true},"family":null,"id":"meta-llama/Llama-3.3-70B-Instruct","knowledge":"2024-10-09","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":70000,"output":70000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct","pricing":null,"provider":"cloudferro_sherlock","provider_model_id":null,"release_date":"2024-12-06","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":2.92,"output":2.92},"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":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-28","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI GPT OSS 120B","pricing":null,"provider":"cloudferro_sherlock","provider_model_id":null,"release_date":"2025-08-28","retired":false,"tags":null},"speakleash/Bielik-11B-v2.6-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":0.67,"output":0.67},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"speakleash/Bielik-11B-v2.6-Instruct","knowledge":"2025-03","last_updated":"2025-03-13","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Bielik 11B v2.6 Instruct","pricing":null,"provider":"cloudferro_sherlock","provider_model_id":null,"release_date":"2025-03-13","retired":false,"tags":null},"speakleash/Bielik-11B-v3.0-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":0.67,"output":0.67},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","llmfit":{"architecture":"llama","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":477778,"hf_likes":81,"matched_hugging_face_id":"speakleash/Bielik-11B-v3.0-Instruct","memory":{"min_ram_gb":6.2,"min_vram_gb":5.7,"recommended_ram_gb":10.4},"model_id":"speakleash/Bielik-11B-v3.0-Instruct","parameter_count":"11.2B","parameters_raw":11168796672,"pipeline_tag":"text-generation","provider":"speakleash","quantization":"Q4_K_M","release_date":"2025-11-07","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"speakleash/Bielik-11B-v3.0-Instruct","knowledge":"2025-03","last_updated":"2025-03-13","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Bielik 11B v3.0 Instruct","pricing":null,"provider":"cloudferro_sherlock","provider_model_id":null,"release_date":"2025-03-13","retired":false,"tags":null}},"name":"CloudFerro Sherlock","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/cloudflare_ai_gateway.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "cloudflare_ai_gateway",
+  "anthropic/claude-3-5-haiku" | "anthropic/claude-3-haiku" | "anthropic/claude-3-opus" | "anthropic/claude-3-sonnet" | "anthropic/claude-3.5-haiku" | "anthropic/claude-3.5-sonnet" | "anthropic/claude-fable-5" | "anthropic/claude-haiku-4-5" | "anthropic/claude-opus-4" | "anthropic/claude-opus-4-1" | "anthropic/claude-opus-4-5" | "anthropic/claude-opus-4-6" | "anthropic/claude-opus-4-7" | "anthropic/claude-opus-4-8" | "anthropic/claude-opus-5" | "anthropic/claude-sonnet-4" | "anthropic/claude-sonnet-4-5" | "anthropic/claude-sonnet-4-6" | "anthropic/claude-sonnet-5" | "moonshotai/kimi-k3" | "openai/gpt-3.5-turbo" | "openai/gpt-4" | "openai/gpt-4-turbo" | "openai/gpt-4o" | "openai/gpt-4o-mini" | "openai/gpt-5.1" | "openai/gpt-5.1-codex" | "openai/gpt-5.2" | "openai/gpt-5.2-codex" | "openai/gpt-5.3-codex" | "openai/gpt-5.4" | "openai/gpt-5.5" | "openai/gpt-5.6-luna" | "openai/gpt-5.6-sol" | "openai/gpt-5.6-terra" | "openai/o1" | "openai/o3" | "openai/o3-mini" | "openai/o3-pro" | "openai/o4-mini" | "workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B" | "workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it" | "workers-ai/@cf/baai/bge-base-en-v1.5" | "workers-ai/@cf/baai/bge-large-en-v1.5" | "workers-ai/@cf/baai/bge-m3" | "workers-ai/@cf/baai/bge-reranker-base" | "workers-ai/@cf/baai/bge-small-en-v1.5" | "workers-ai/@cf/deepgram/aura-2-en" | "workers-ai/@cf/deepgram/aura-2-es" | "workers-ai/@cf/deepgram/nova-3" | "workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b" | "workers-ai/@cf/facebook/bart-large-cnn" | "workers-ai/@cf/google/gemma-3-12b-it" | "workers-ai/@cf/huggingface/distilbert-sst-2-int8" | "workers-ai/@cf/ibm-granite/granite-4.0-h-micro" | "workers-ai/@cf/meta/llama-2-7b-chat-fp16" | "workers-ai/@cf/meta/llama-3-8b-instruct" | "workers-ai/@cf/meta/llama-3-8b-instruct-awq" | "workers-ai/@cf/meta/llama-3.1-8b-instruct" | "workers-ai/@cf/meta/llama-3.1-8b-instruct-awq" | "workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8" | "workers-ai/@cf/meta/llama-3.2-11b-vision-instruct" | "workers-ai/@cf/meta/llama-3.2-1b-instruct" | "workers-ai/@cf/meta/llama-3.2-3b-instruct" | "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast" | "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct" | "workers-ai/@cf/meta/llama-guard-3-8b" | "workers-ai/@cf/meta/m2m100-1.2b" | "workers-ai/@cf/mistral/mistral-7b-instruct-v0.1" | "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct" | "workers-ai/@cf/moonshotai/kimi-k2.5" | "workers-ai/@cf/moonshotai/kimi-k2.6" | "workers-ai/@cf/myshell-ai/melotts" | "workers-ai/@cf/nvidia/nemotron-3-120b-a12b" | "workers-ai/@cf/openai/gpt-oss-120b" | "workers-ai/@cf/openai/gpt-oss-20b" | "workers-ai/@cf/pfnet/plamo-embedding-1b" | "workers-ai/@cf/pipecat-ai/smart-turn-v2" | "workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct" | "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8" | "workers-ai/@cf/qwen/qwen3-embedding-0.6b" | "workers-ai/@cf/qwen/qwq-32b" | "workers-ai/@cf/zai-org/glm-4.7-flash" | "workers-ai/@cf/zai-org/glm-5.2"
+>;
+export default provider;

package/dist/providers/cloudflare_ai_gateway.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":null,"catalog_only":true,"config_schema":null,"doc":"https://developers.cloudflare.com/ai-gateway/","env":["CLOUDFLARE_API_TOKEN","CLOUDFLARE_ACCOUNT_ID","CLOUDFLARE_GATEWAY_ID"],"exclude_models":null,"extra":null,"id":"cloudflare_ai_gateway","models":{"anthropic/claude-3-5-haiku":{"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":0.08,"cache_write":1,"input":0.8,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"temperature":true},"family":null,"id":"anthropic/claude-3-5-haiku","knowledge":"2024-07-31","last_updated":"2024-10-22","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Haiku 3.5 (latest)","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2024-10-22","retired":false,"tags":null},"anthropic/claude-3-haiku":{"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":0.03,"cache_write":0.3,"input":0.25,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"temperature":true},"family":null,"id":"anthropic/claude-3-haiku","knowledge":"2023-08-31","last_updated":"2024-03-13","lifecycle":null,"limits":{"context":200000,"output":4096},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Haiku 3","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2024-03-13","retired":false,"tags":null},"anthropic/claude-3-opus":{"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":1.5,"cache_write":18.75,"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,"temperature":true},"family":null,"id":"anthropic/claude-3-opus","knowledge":"2023-08-31","last_updated":"2024-02-29","lifecycle":null,"limits":{"context":200000,"output":4096},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 3","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2024-02-29","retired":false,"tags":null},"anthropic/claude-3-sonnet":{"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":0.3,"cache_write":0.3,"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,"temperature":true},"family":null,"id":"anthropic/claude-3-sonnet","knowledge":"2023-08-31","last_updated":"2024-03-04","lifecycle":null,"limits":{"context":200000,"output":4096},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 3","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2024-03-04","retired":false,"tags":null},"anthropic/claude-3.5-haiku":{"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":0.08,"cache_write":1,"input":0.8,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"temperature":true},"family":null,"id":"anthropic/claude-3.5-haiku","knowledge":"2024-07-31","last_updated":"2024-10-22","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Haiku 3.5 (latest)","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2024-10-22","retired":false,"tags":null},"anthropic/claude-3.5-sonnet":{"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":0.3,"cache_write":3.75,"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,"temperature":true},"family":null,"id":"anthropic/claude-3.5-sonnet","knowledge":"2024-04-30","last_updated":"2024-10-22","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 3.5 v2","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2024-10-22","retired":false,"tags":null},"anthropic/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":{"cache_read":1,"cache_write":12.5,"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":[{"type":"effort","values":["low","medium","high"]}],"temperature":false},"family":null,"id":"anthropic/claude-fable-5","knowledge":"2026-01-31","last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Fable 5","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"anthropic/claude-haiku-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":{"cache_read":0.1,"cache_write":1.25,"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":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic/claude-haiku-4-5","knowledge":"2025-02-28","last_updated":"2025-10-15","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Haiku 4.5 (latest)","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"anthropic/claude-opus-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":1.5,"cache_write":18.75,"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":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic/claude-opus-4","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4 (latest)","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"anthropic/claude-opus-4-1":{"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":1.5,"cache_write":18.75,"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":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic/claude-opus-4-1","knowledge":"2025-03-31","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 (latest)","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"anthropic/claude-opus-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":{"cache_read":0.5,"cache_write":6.25,"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":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic/claude-opus-4-5","knowledge":"2025-03-31","last_updated":"2025-11-24","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.5 (latest)","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-11-24","retired":false,"tags":null},"anthropic/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":{"cache_read":0.5,"cache_write":6.25,"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":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic/claude-opus-4-6","knowledge":"2025-05-31","last_updated":"2026-02-05","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.6 (latest)","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"anthropic/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":{"cache_read":0.5,"cache_write":6.25,"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,"provider":{"npm":"@ai-sdk/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"anthropic/claude-opus-4-7","knowledge":"2026-01","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"anthropic/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":{"cache_read":0.5,"cache_write":6.25,"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":[{"type":"effort","values":["low","medium","high"]}],"temperature":false},"family":null,"id":"anthropic/claude-opus-4-8","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"anthropic/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":{"cache_read":0.5,"cache_write":6.25,"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":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"anthropic/claude-opus-5","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"anthropic/claude-sonnet-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":0.3,"cache_write":3.75,"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":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4 (latest)","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"anthropic/claude-sonnet-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":{"cache_read":0.3,"cache_write":3.75,"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":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4-5","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5 (latest)","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"anthropic/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":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","interleaved":true,"open_weights":false,"provider":{"npm":"ai-gateway-provider"},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4-6","knowledge":"2025-08-31","last_updated":"2026-02-17","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"anthropic/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":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","interleaved":true,"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"anthropic/claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-06-30","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","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["max"]}],"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":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"openai/gpt-3.5-turbo":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":1.25,"input":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"openai/gpt-3.5-turbo","knowledge":"2021-09-01","last_updated":"2023-11-06","lifecycle":null,"limits":{"context":16385,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-3.5-turbo","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2023-03-01","retired":false,"tags":null},"openai/gpt-4":{"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":30,"output":60},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"openai/gpt-4","knowledge":"2023-11","last_updated":"2024-04-09","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-4","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"openai/gpt-4-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":10,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"openai/gpt-4-turbo","knowledge":"2023-12","last_updated":"2024-04-09","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4 Turbo","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"openai/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":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/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":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"openai/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":{"cache_read":0.08,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/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":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"openai/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":0.13,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"temperature":false},"family":null,"id":"openai/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":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/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":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/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":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/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":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"temperature":false},"family":null,"id":"openai/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":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai/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":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"provider":{"npm":"ai-gateway-provider"},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.2-codex","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.2 Codex","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai/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":0.175,"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,"provider":{"npm":"ai-gateway-provider"},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.3-codex","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","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"openai/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":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","open_weights":false,"provider":{"npm":"ai-gateway-provider"},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.4","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.4","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai/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":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"openai/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":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.6-luna","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Luna","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/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":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.6-sol","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/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":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.6-terra","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Terra","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/o1":{"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":7.5,"input":15,"output":60},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o1","knowledge":"2023-09","last_updated":"2024-12-05","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o1","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"openai/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":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/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":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"openai/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":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/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":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2024-12-20","retired":false,"tags":null},"openai/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":80},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/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":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-06-10","retired":false,"tags":null},"openai/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":{"cache_read":0.28,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/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":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.34,"output":0.34},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"indictrans","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B","knowledge":null,"last_updated":"2025-09-25","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"IndicTrans2 EN-Indic 1B","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-09-25","retired":false,"tags":null},"workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.35,"output":0.56},"deprecated":false,"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it","knowledge":null,"last_updated":"2025-09-25","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma SEA-LION v4 27B IT","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-09-25","retired":false,"tags":null},"workers-ai/@cf/baai/bge-base-en-v1.5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.067,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"bge","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/baai/bge-base-en-v1.5","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"BGE Base EN v1.5","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/baai/bge-large-en-v1.5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.2,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"bge","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/baai/bge-large-en-v1.5","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"BGE Large EN v1.5","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/baai/bge-m3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.012,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"bge","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/baai/bge-m3","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"BGE M3","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/baai/bge-reranker-base":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.0031,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"bge","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/baai/bge-reranker-base","knowledge":null,"last_updated":"2025-04-09","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"BGE Reranker Base","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-09","retired":false,"tags":null},"workers-ai/@cf/baai/bge-small-en-v1.5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.02,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"bge","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/baai/bge-small-en-v1.5","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"BGE Small EN v1.5","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/deepgram/aura-2-en":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"aura","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/deepgram/aura-2-en","knowledge":null,"last_updated":"2025-11-14","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepgram Aura 2 (EN)","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-11-14","retired":false,"tags":null},"workers-ai/@cf/deepgram/aura-2-es":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"aura","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/deepgram/aura-2-es","knowledge":null,"last_updated":"2025-11-14","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepgram Aura 2 (ES)","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-11-14","retired":false,"tags":null},"workers-ai/@cf/deepgram/nova-3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"nova","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/deepgram/nova-3","knowledge":null,"last_updated":"2025-11-14","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepgram Nova 3","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-11-14","retired":false,"tags":null},"workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.5,"output":4.88},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"deepseek-thinking","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1 Distill Qwen 32B","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/facebook/bart-large-cnn":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"bart","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/facebook/bart-large-cnn","knowledge":null,"last_updated":"2025-04-09","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"BART Large CNN","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-09","retired":false,"tags":null},"workers-ai/@cf/google/gemma-3-12b-it":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.35,"output":0.56},"deprecated":false,"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/google/gemma-3-12b-it","knowledge":null,"last_updated":"2025-04-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma 3 12B IT","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-11","retired":false,"tags":null},"workers-ai/@cf/huggingface/distilbert-sst-2-int8":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.026,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"distilbert","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/huggingface/distilbert-sst-2-int8","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DistilBERT SST-2 INT8","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/ibm-granite/granite-4.0-h-micro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.017,"output":0.11},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"granite","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/ibm-granite/granite-4.0-h-micro","knowledge":null,"last_updated":"2025-10-15","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"IBM Granite 4.0 H Micro","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"workers-ai/@cf/meta/llama-2-7b-chat-fp16":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.56,"output":6.67},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/meta/llama-2-7b-chat-fp16","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 2 7B Chat FP16","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/meta/llama-3-8b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.28,"output":0.83},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/meta/llama-3-8b-instruct","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3 8B Instruct","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/meta/llama-3-8b-instruct-awq":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.12,"output":0.27},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/meta/llama-3-8b-instruct-awq","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3 8B Instruct AWQ","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/meta/llama-3.1-8b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.28,"output":0.8299999999999998},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/meta/llama-3.1-8b-instruct","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B Instruct","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/meta/llama-3.1-8b-instruct-awq":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.12,"output":0.27},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/meta/llama-3.1-8b-instruct-awq","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B Instruct AWQ","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.15,"output":0.29},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B Instruct FP8","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/meta/llama-3.2-11b-vision-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.049,"output":0.68},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/meta/llama-3.2-11b-vision-instruct","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 11B Vision Instruct","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/meta/llama-3.2-1b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.027,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/meta/llama-3.2-1b-instruct","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 1B Instruct","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/meta/llama-3.2-3b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.051,"output":0.34},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/meta/llama-3.2-3b-instruct","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 3B Instruct","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.29,"output":2.25},"deprecated":false,"extra":{"attachment":false,"description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct FP8 Fast","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.27,"output":0.85},"deprecated":false,"extra":{"attachment":false,"description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct","knowledge":null,"last_updated":"2025-04-16","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 4 Scout 17B 16E Instruct","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"workers-ai/@cf/meta/llama-guard-3-8b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.48,"output":0.03},"deprecated":false,"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/meta/llama-guard-3-8b","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama Guard 3 8B","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/meta/m2m100-1.2b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.34,"output":0.34},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"m2m","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/meta/m2m100-1.2b","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"M2M100 1.2B","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/mistral/mistral-7b-instruct-v0.1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.11,"output":0.19},"deprecated":false,"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/mistral/mistral-7b-instruct-v0.1","knowledge":null,"last_updated":"2025-04-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral 7B Instruct v0.1","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-03","retired":false,"tags":null},"workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.35,"output":0.56},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct","knowledge":null,"last_updated":"2025-04-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Small 3.1 24B Instruct","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-11","retired":false,"tags":null},"workers-ai/@cf/moonshotai/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":{"cache_read":0.1,"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"workers-ai/@cf/moonshotai/kimi-k2.5","knowledge":"2025-01","last_updated":"2026-01-27","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"workers-ai/@cf/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":0.16,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"workers-ai/@cf/moonshotai/kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-20","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"workers-ai/@cf/myshell-ai/melotts":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"melotts","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/myshell-ai/melotts","knowledge":null,"last_updated":"2025-11-14","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MyShell MeloTTS","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-11-14","retired":false,"tags":null},"workers-ai/@cf/nvidia/nemotron-3-120b-a12b":{"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":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"workers-ai/@cf/nvidia/nemotron-3-120b-a12b","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Super 120B","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"workers-ai/@cf/openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.35,"output":0.75},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/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":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"workers-ai/@cf/openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.2,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"workers-ai/@cf/pfnet/plamo-embedding-1b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.019,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"plamo","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/pfnet/plamo-embedding-1b","knowledge":null,"last_updated":"2025-09-25","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"PLaMo Embedding 1B","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-09-25","retired":false,"tags":null},"workers-ai/@cf/pipecat-ai/smart-turn-v2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"smart-turn","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/pipecat-ai/smart-turn-v2","knowledge":null,"last_updated":"2025-11-14","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Pipecat Smart Turn v2","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-11-14","retired":false,"tags":null},"workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.66,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct","knowledge":null,"last_updated":"2025-04-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 2.5 Coder 32B Instruct","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-11","retired":false,"tags":null},"workers-ai/@cf/qwen/qwen3-30b-a3b-fp8":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.051,"output":0.34},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/qwen/qwen3-30b-a3b-fp8","knowledge":null,"last_updated":"2025-11-14","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B FP8","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-11-14","retired":false,"tags":null},"workers-ai/@cf/qwen/qwen3-embedding-0.6b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.012,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/qwen/qwen3-embedding-0.6b","knowledge":null,"last_updated":"2025-11-14","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Embedding 0.6B","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-11-14","retired":false,"tags":null},"workers-ai/@cf/qwen/qwq-32b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.66,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"workers-ai/@cf/qwen/qwq-32b","knowledge":null,"last_updated":"2025-04-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"QwQ 32B","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2025-04-11","retired":false,"tags":null},"workers-ai/@cf/zai-org/glm-4.7-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":{"input":0.06,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"workers-ai/@cf/zai-org/glm-4.7-flash","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-Flash","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"workers-ai/@cf/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","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"workers-ai/@cf/zai-org/glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Glm 5.2","pricing":null,"provider":"cloudflare_ai_gateway","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Cloudflare AI Gateway","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/cloudflare_workers_ai.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "cloudflare_workers_ai",
+  "@cf/aisingapore/gemma-sea-lion-v4-27b-it" | "@cf/deepseek-ai/deepseek-r1-distill-qwen-32b" | "@cf/google/gemma-4-26b-a4b-it" | "@cf/ibm-granite/granite-4.0-h-micro" | "@cf/meta/llama-3.1-8b-instruct-fp8" | "@cf/meta/llama-3.2-11b-vision-instruct" | "@cf/meta/llama-3.2-1b-instruct" | "@cf/meta/llama-3.2-3b-instruct" | "@cf/meta/llama-3.3-70b-instruct-fp8-fast" | "@cf/meta/llama-4-scout-17b-16e-instruct" | "@cf/meta/llama-guard-3-8b" | "@cf/mistralai/mistral-small-3.1-24b-instruct" | "@cf/moonshotai/kimi-k2.6" | "@cf/moonshotai/kimi-k2.7-code" | "@cf/nvidia/nemotron-3-120b-a12b" | "@cf/openai/gpt-oss-120b" | "@cf/openai/gpt-oss-20b" | "@cf/qwen/qwen2.5-coder-32b-instruct" | "@cf/qwen/qwen3-30b-a3b-fp8" | "@cf/qwen/qwq-32b" | "@cf/zai-org/glm-4.7-flash" | "@cf/zai-org/glm-5.2"
+>;
+export default provider;