@agentjido/llmdb 2026.8.2 → 2026.8.3

package/dist/providers/cloudflare_workers_ai.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1","config_schema":null,"doc":"https://developers.cloudflare.com/workers-ai/models/","env":["CLOUDFLARE_ACCOUNT_ID","CLOUDFLARE_API_KEY"],"exclude_models":null,"extra":null,"id":"cloudflare_workers_ai","models":{"@cf/aisingapore/gemma-sea-lion-v4-27b-it":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.351,"output":0.555},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/aisingapore/gemma-sea-lion-v4-27b-it","knowledge":null,"last_updated":"2025-09-23","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma Sea Lion V4 27B It","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.497,"output":4.881},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","knowledge":"2024-07","last_updated":"2025-05-29","lifecycle":null,"limits":{"context":80000,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek R1 Distill Qwen 32B","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"@cf/google/gemma-4-26b-a4b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","interleaved":true,"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"@cf/google/gemma-4-26b-a4b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B IT","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"@cf/ibm-granite/granite-4.0-h-micro":{"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}},"cost":{"input":0.017,"output":0.112},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"granite","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/ibm-granite/granite-4.0-h-micro","knowledge":null,"last_updated":"2025-10-07","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Granite 4.0 H Micro","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-10-07","retired":false,"tags":null},"@cf/meta/llama-3.1-8b-instruct-fp8":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.152,"output":0.287},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-3.1-8b-instruct-fp8","knowledge":null,"last_updated":"2024-07-25","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B Instruct fp8","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2024-07-25","retired":false,"tags":null},"@cf/meta/llama-3.2-11b-vision-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0485,"output":0.676},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-3.2-11b-vision-instruct","knowledge":null,"last_updated":"2024-09-25","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 3.2 11B Vision Instruct","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2024-09-25","retired":false,"tags":null},"@cf/meta/llama-3.2-1b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.027,"output":0.201},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-3.2-1b-instruct","knowledge":null,"last_updated":"2024-09-25","lifecycle":null,"limits":{"context":60000,"output":60000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 1B Instruct","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2024-09-25","retired":false,"tags":null},"@cf/meta/llama-3.2-3b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0509,"output":0.335},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-3.2-3b-instruct","knowledge":null,"last_updated":"2024-09-25","lifecycle":null,"limits":{"context":80000,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 3B Instruct","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2024-09-25","retired":false,"tags":null},"@cf/meta/llama-3.3-70b-instruct-fp8-fast":{"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}},"cost":{"input":0.293,"output":2.253},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":24000,"output":24000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct fp8 Fast","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"@cf/meta/llama-4-scout-17b-16e-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}},"cost":{"input":0.27,"output":0.85},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-4-scout-17b-16e-instruct","knowledge":"2024-08","last_updated":"2025-04-05","lifecycle":null,"limits":{"context":131000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Scout 17B 16E Instruct","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"@cf/meta/llama-guard-3-8b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.484,"output":0.03},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-guard-3-8b","knowledge":null,"last_updated":"2025-01-22","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama Guard 3 8B","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-01-22","retired":false,"tags":null},"@cf/mistralai/mistral-small-3.1-24b-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}},"cost":{"input":0.351,"output":0.555},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/mistralai/mistral-small-3.1-24b-instruct","knowledge":null,"last_updated":"2025-03-18","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Small 3.1 24B Instruct","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-03-18","retired":false,"tags":null},"@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}},"cost":{"cache_read":0.16,"input":0.95,"output":4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"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"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"@cf/moonshotai/kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"@cf/moonshotai/kimi-k2.7-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.19,"input":0.95,"output":4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"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":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"@cf/moonshotai/kimi-k2.7-code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"@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}},"cost":{"input":0.5,"output":1.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","interleaved":true,"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"@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_workers_ai","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"@cf/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}},"cost":{"input":0.35,"output":0.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"@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_workers_ai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"@cf/openai/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}},"cost":{"input":0.2,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"@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_workers_ai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"@cf/qwen/qwen2.5-coder-32b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.66,"output":1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/qwen/qwen2.5-coder-32b-instruct","knowledge":null,"last_updated":"2025-02-27","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen2.5 Coder 32B Instruct","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-02-27","retired":false,"tags":null},"@cf/qwen/qwen3-30b-a3b-fp8":{"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}},"cost":{"input":0.0509,"output":0.335},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"@cf/qwen/qwen3-30b-a3b-fp8","knowledge":null,"last_updated":"2025-04-30","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3b fp8","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-04-30","retired":false,"tags":null},"@cf/qwen/qwq-32b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.66,"output":1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"@cf/qwen/qwq-32b","knowledge":null,"last_updated":"2025-03-05","lifecycle":null,"limits":{"context":24000,"output":24000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwq 32B","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-03-05","retired":false,"tags":null},"@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}},"cost":{"input":0.0605,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","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":"@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_workers_ai","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"@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}},"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"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":"@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_workers_ai","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Cloudflare Workers AI","pricing_defaults":null,"runtime":{"auth":{"env":["CLOUDFLARE_API_KEY"],"headers":[],"type":"bearer"},"base_url":"https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1","config_schema":[{"doc":"Cloudflare account ID used in the Workers AI base URL template.","name":"account_id","required":true,"type":"string"}],"default_headers":{},"default_query":{},"doc_url":"https://developers.cloudflare.com/workers-ai/models/"}};
+export const data = {"alias_of":null,"base_url":"https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1","config_schema":null,"doc":"https://developers.cloudflare.com/workers-ai/models/","env":["CLOUDFLARE_ACCOUNT_ID","CLOUDFLARE_API_KEY"],"exclude_models":null,"extra":null,"id":"cloudflare_workers_ai","models":{"@cf/aisingapore/gemma-sea-lion-v4-27b-it":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.351,"output":0.555},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/aisingapore/gemma-sea-lion-v4-27b-it","knowledge":null,"last_updated":"2025-09-23","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma Sea Lion V4 27B It","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.497,"output":4.881},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","knowledge":"2024-07","last_updated":"2025-05-29","lifecycle":null,"limits":{"context":80000,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek R1 Distill Qwen 32B","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"@cf/deepseek-ai/deepseek-v4-flash-0731":{"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}},"cost":{"cache_read":0.014,"input":0.44,"output":1.32},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"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"},{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"@cf/deepseek-ai/deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1310720,"output":1048576},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"@cf/deepseek-ai/deepseek-v4-pro-0813":{"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}},"cost":{"cache_read":0.044,"input":1.32,"output":3.96},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"@cf/deepseek-ai/deepseek-v4-pro-0813","knowledge":null,"last_updated":"2026-08-12","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro 0813","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"@cf/google/gemma-4-26b-a4b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","interleaved":true,"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"@cf/google/gemma-4-26b-a4b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B IT","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"@cf/ibm-granite/granite-4.0-h-micro":{"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}},"cost":{"input":0.017,"output":0.112},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"granite","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/ibm-granite/granite-4.0-h-micro","knowledge":null,"last_updated":"2025-10-07","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Granite 4.0 H Micro","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-10-07","retired":false,"tags":null},"@cf/meta/llama-3.1-8b-instruct-fp8":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.152,"output":0.287},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-3.1-8b-instruct-fp8","knowledge":"2023-12","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B Instruct fp8","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"@cf/meta/llama-3.2-11b-vision-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0485,"output":0.676},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-3.2-11b-vision-instruct","knowledge":"2023-12","last_updated":"2024-09-25","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 3.2 11B Vision Instruct","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2024-09-25","retired":false,"tags":null},"@cf/meta/llama-3.2-1b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.027,"output":0.201},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-3.2-1b-instruct","knowledge":"2023-12","last_updated":"2024-09-25","lifecycle":null,"limits":{"context":60000,"output":60000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 1B Instruct","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2024-09-25","retired":false,"tags":null},"@cf/meta/llama-3.2-3b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0509,"output":0.335},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-3.2-3b-instruct","knowledge":"2023-12","last_updated":"2024-09-25","lifecycle":null,"limits":{"context":80000,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 3B Instruct","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2024-09-25","retired":false,"tags":null},"@cf/meta/llama-3.3-70b-instruct-fp8-fast":{"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}},"cost":{"input":0.293,"output":2.253},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":24000,"output":24000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct fp8 Fast","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"@cf/meta/llama-4-scout-17b-16e-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}},"cost":{"input":0.27,"output":0.85},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-4-scout-17b-16e-instruct","knowledge":"2024-08","last_updated":"2025-04-05","lifecycle":null,"limits":{"context":131000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Scout 17B 16E Instruct","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"@cf/meta/llama-guard-3-8b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.484,"output":0.03},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/meta/llama-guard-3-8b","knowledge":"2023-12","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama Guard 3 8B","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"@cf/mistralai/mistral-small-3.1-24b-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}},"cost":{"input":0.351,"output":0.555},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/mistralai/mistral-small-3.1-24b-instruct","knowledge":null,"last_updated":"2025-03-18","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Small 3.1 24B Instruct","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-03-18","retired":false,"tags":null},"@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}},"cost":{"cache_read":0.16,"input":0.95,"output":4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"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"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"@cf/moonshotai/kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"@cf/moonshotai/kimi-k2.7-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.19,"input":0.95,"output":4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"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":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"@cf/moonshotai/kimi-k2.7-code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"@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}},"cost":{"input":0.5,"output":1.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","interleaved":true,"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"@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_workers_ai","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"@cf/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}},"cost":{"input":0.35,"output":0.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"@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_workers_ai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"@cf/openai/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}},"cost":{"input":0.2,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"@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_workers_ai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"@cf/qwen/qwen2.5-coder-32b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.66,"output":1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"@cf/qwen/qwen2.5-coder-32b-instruct","knowledge":null,"last_updated":"2024-11-12","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen2.5 Coder 32B Instruct","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2024-11-12","retired":false,"tags":null},"@cf/qwen/qwen3-30b-a3b-fp8":{"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}},"cost":{"input":0.0509,"output":0.335},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"@cf/qwen/qwen3-30b-a3b-fp8","knowledge":null,"last_updated":"2025-04-28","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3b fp8","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"@cf/qwen/qwq-32b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.66,"output":1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"@cf/qwen/qwq-32b","knowledge":"2024-04","last_updated":"2025-03-05","lifecycle":null,"limits":{"context":24000,"output":24000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwq 32B","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2025-03-05","retired":false,"tags":null},"@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}},"cost":{"input":0.0605,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","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":"@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_workers_ai","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"@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}},"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"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":"@cf/zai-org/glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":262144,"output":256000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Glm 5.2","pricing":null,"provider":"cloudflare_workers_ai","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Cloudflare Workers AI","pricing_defaults":null,"runtime":{"auth":{"env":["CLOUDFLARE_API_KEY"],"headers":[],"type":"bearer"},"base_url":"https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1","config_schema":[{"doc":"Cloudflare account ID used in the Workers AI base URL template.","name":"account_id","required":true,"type":"string"}],"default_headers":{},"default_query":{},"doc_url":"https://developers.cloudflare.com/workers-ai/models/"}};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/coralbricks.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "coralbricks",
+  "glm-5.2-fp4" | "gpt-oss-120b" | "kimi-k3"
+>;
+export default provider;

package/dist/providers/coralbricks.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://inference.coralbricks.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://www.coralbricks.ai/docs","env":["CORAL_API_KEY"],"exclude_models":null,"extra":null,"id":"coralbricks","models":{"glm-5.2-fp4":{"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,"input":1.12,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","interleaved":true,"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-fp4","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 FP4","pricing":null,"provider":"coralbricks","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"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":{"cache_read":0,"input":0.12,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","interleaved":true,"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"coralbricks","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"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,"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":true,"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"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":"coralbricks","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null}},"name":"CoralBricks","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/cortecs.d.ts

@@ -6,6 +6,6 @@ import type {
 export declare const data: Provider;
 declare const provider: ProviderCatalog<
   "cortecs",
-  "claude-4-5-sonnet" | "claude-4-6-sonnet" | "claude-haiku-4-5" | "claude-opus4-5" | "claude-opus4-6" | "claude-opus4-7" | "claude-opus4-8" | "claude-sonnet-4" | "codestral-2508" | "deepseek-r1-0528" | "deepseek-v3-0324" | "deepseek-v3.2" | "deepseek-v4-flash" | "deepseek-v4-flash-0731" | "deepseek-v4-pro" | "devstral-2512" | "gemini-2.5-pro" | "glm-4.5" | "glm-4.5-air" | "glm-4.7" | "glm-4.7-flash" | "glm-5" | "glm-5-turbo" | "glm-5.1" | "glm-5.2" | "glm-5v-turbo" | "gpt-4.1" | "gpt-5.4" | "gpt-oss-120b" | "hermes-4-70b" | "hy3" | "intellect-3" | "kimi-k2-instruct" | "kimi-k2-thinking" | "kimi-k2.5" | "kimi-k2.6" | "kimi-k2.7-code" | "kimi-k3" | "llama-3.1-405b-instruct" | "llama-3.3-70b-instruct" | "llama-4-maverick" | "minimax-m2" | "minimax-m2.1" | "minimax-m2.5" | "minimax-m2.7" | "minimax-m3" | "mistral-large-2512" | "mixtral-8x7B-instruct-v0.1" | "nemotron-3-super-120b-a12b" | "nova-pro-v1" | "qwen-2.5-72b-instruct" | "qwen3-235b-a22b-instruct-2507" | "qwen3-32b" | "qwen3-coder-30b-a3b-instruct" | "qwen3-coder-480b-a35b-instruct" | "qwen3-coder-next" | "qwen3-next-80b-a3b-thinking" | "qwen3.5-122b-a10b" | "qwen3.5-397b-a17b"
+  "apertus-70b" | "claude-4-5-sonnet" | "claude-4-6-sonnet" | "claude-haiku-4-5" | "claude-opus-5" | "claude-opus4-5" | "claude-opus4-6" | "claude-opus4-7" | "claude-opus4-8" | "claude-sonnet-4" | "claude-sonnet-5" | "codestral-2508" | "cosmos3-super-reasoner" | "deepseek-r1-0528" | "deepseek-v3.2" | "deepseek-v4-flash-0731" | "deepseek-v4-pro" | "devstral-2512" | "gemini-2.5-flash" | "gemini-2.5-pro" | "gemini-3.1-flash-lite" | "gemini-3.5-flash" | "gemini-3.5-flash-lite" | "gemini-3.6-flash" | "gemini-3.7-flash" | "gemma-3-27b-it" | "gemma-4-26b-a4b-it" | "gemma-4-31b-it" | "glm-4.7" | "glm-4.7-flash" | "glm-5" | "glm-5-turbo" | "glm-5.1" | "glm-5.2" | "glm-5v-turbo" | "gpt-4.1" | "gpt-4.1-mini" | "gpt-4.1-nano" | "gpt-4o" | "gpt-4o-mini" | "gpt-5" | "gpt-5-mini" | "gpt-5-nano" | "gpt-5.1" | "gpt-5.4" | "gpt-5.6-luna" | "gpt-5.6-sol" | "gpt-5.6-terra" | "gpt-oss-120b" | "gpt-oss-20b" | "gpt-oss-safeguard-120b" | "hermes-4-405b" | "hermes-4-70b" | "kimi-k2.5" | "kimi-k2.6" | "kimi-k2.7-code" | "kimi-k3" | "llama-3.1-405b-instruct" | "llama-3.1-8b-instruct" | "llama-3.1-nemotron-ultra-253b-v1" | "llama-3.3-70b-instruct" | "minicpm-v-4.5" | "minimax-m2" | "minimax-m2.1" | "minimax-m2.5" | "minimax-m2.7" | "minimax-m3" | "ministral-14b-2512" | "ministral-3b-2512" | "ministral-8b-2512" | "mistral-7b-instruct-v0.2" | "mistral-7b-instruct-v0.3" | "mistral-large-2402" | "mistral-large-2512" | "mistral-medium-2508" | "mistral-medium-3.5" | "mistral-nemo-instruct-2407" | "mistral-small-2503" | "mistral-small-2603" | "mistral-small-3.2-24b-instruct-2506" | "mixtral-8x7B-instruct-v0.1" | "nemotron-nano-v2-12b" | "nova-2-lite" | "nova-lite-v1" | "nova-micro-v1" | "nova-pro-v1" | "nvidia-nemotron-3-nano-30b-a3b" | "nvidia-nemotron-3-nano-omni" | "pixtral-12b-2409" | "pixtral-large-2502" | "qwen2.5-vl-72b-instruct" | "qwen3-235b-a22b-instruct-2507" | "qwen3-30b-a3b-instruct-2507" | "qwen3-32b" | "qwen3-coder-30b-a3b-instruct" | "qwen3-coder-next" | "qwen3-next-80b-a3b-thinking" | "qwen3-vl-235b-a22b" | "qwen3.5-122b-a10b" | "qwen3.5-397b-a17b" | "qwen3.5-9b" | "qwen3.6-27b" | "qwen3.6-35b-a3b" | "qwen3.8-2.4t-a95b" | "qwen3guard-gen-0.6b" | "qwen3guard-gen-8b" | "voxtral-small-2507"
 >;
 export default provider;