@agentjido/llmdb 2026.8.2

package/dist/providers/azure_cognitive_services.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":null,"catalog_only":true,"config_schema":[{"doc":"Azure AI Foundry API base URL (e.g. https://{instance_name}.openai.azure.com)","name":"base_url","required":true,"type":"string"},{"doc":"Azure AI Foundry deployment name for the model to use","name":"deployment_name","required":false,"type":"string"},{"doc":"Azure AI Foundry API version to use (e.g. 2024-06-01)","name":"api_version","required":false,"type":"string"}],"doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","env":["AZURE_COGNITIVE_SERVICES_RESOURCE_NAME","AZURE_COGNITIVE_SERVICES_API_KEY"],"exclude_models":null,"extra":null,"id":"azure_cognitive_services","models":{"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,"provider":{"api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1","npm":"@ai-sdk/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":true,"wire_protocol":"anthropic_messages"},"family":null,"id":"claude-haiku-4-5","knowledge":"2025-02-28","last_updated":"2025-11-18","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Haiku 4.5","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"claude-opus-4-1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"provider":{"api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1","npm":"@ai-sdk/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":true,"wire_protocol":"anthropic_messages"},"family":null,"id":"claude-opus-4-1","knowledge":"2025-03-31","last_updated":"2025-11-18","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.1","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"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,"provider":{"api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1","npm":"@ai-sdk/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"min":1024,"type":"budget_tokens"}],"temperature":true,"wire_protocol":"anthropic_messages"},"family":null,"id":"claude-opus-4-5","knowledge":"2025-03-31","last_updated":"2025-08-01","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.5","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-11-24","retired":false,"tags":null},"claude-opus-4-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"provider":{"api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1","npm":"@ai-sdk/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"min":1024,"type":"budget_tokens"}],"temperature":true,"wire_protocol":"anthropic_messages"},"family":null,"id":"claude-opus-4-6","knowledge":"2025-05-31","last_updated":"2026-07-17","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.6","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"claude-opus-4-8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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,"provider":{"api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1","npm":"@ai-sdk/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false,"wire_protocol":"anthropic_messages"},"family":null,"id":"claude-opus-4-8","knowledge":"2025-12-31","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"claude-opus-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","open_weights":false,"provider":{"api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1","npm":"@ai-sdk/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false,"wire_protocol":"anthropic_messages"},"family":null,"id":"claude-opus-5","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"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,"provider":{"api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1","npm":"@ai-sdk/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":true,"wire_protocol":"anthropic_messages"},"family":null,"id":"claude-sonnet-4-5","knowledge":"2025-07-31","last_updated":"2025-11-18","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"codestral-2501":{"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":0.9},"deprecated":false,"extra":{"attachment":false,"description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","open_weights":false,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"codestral-2501","knowledge":"2024-03","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Codestral 25.01","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"codex-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":0.375,"input":1.5,"output":6},"deprecated":false,"extra":{"api":"responses","attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"deprecated","temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"codex-mini","knowledge":"2024-04","last_updated":"2025-05-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Codex Mini","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-05-16","retired":false,"tags":null},"cohere-command-a":{"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":10},"deprecated":false,"extra":{"attachment":false,"description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","open_weights":true,"reasoning_options":[],"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"cohere-command-a","knowledge":"2024-06-01","last_updated":"2025-03-13","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Command A","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-03-13","retired":false,"tags":null},"cohere-embed-v-4-0":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1536,"max_dimensions":1536,"min_dimensions":256},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.12,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","open_weights":true,"temperature":false,"type":"embedding"},"family":null,"id":"cohere-embed-v-4-0","knowledge":null,"last_updated":"2025-04-15","lifecycle":null,"limits":{"context":128000,"output":1536},"modalities":{"input":["text","image"],"output":["text","embedding"]},"model":null,"name":"Embed v4","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-04-15","retired":false,"tags":null},"cohere-embed-v3-english":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1024,"max_dimensions":1024,"min_dimensions":1024},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.1,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","open_weights":true,"temperature":false,"type":"embedding"},"family":null,"id":"cohere-embed-v3-english","knowledge":null,"last_updated":"2023-11-07","lifecycle":null,"limits":{"context":512,"output":1024},"modalities":{"input":["text"],"output":["text","embedding"]},"model":null,"name":"Embed v3 English","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2023-11-07","retired":false,"tags":null},"cohere-embed-v3-multilingual":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1024,"max_dimensions":1024,"min_dimensions":1024},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.1,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","open_weights":true,"temperature":false,"type":"embedding"},"family":null,"id":"cohere-embed-v3-multilingual","knowledge":null,"last_updated":"2023-11-07","lifecycle":null,"limits":{"context":512,"output":1024},"modalities":{"input":["text"],"output":["text","embedding"]},"model":null,"name":"Embed v3 Multilingual","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2023-11-07","retired":false,"tags":null},"deepseek-r1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":1.35,"output":5.4},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","open_weights":true,"reasoning_options":[],"status":"deprecated","temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"deepseek-r1","knowledge":"2024-07","last_updated":"2025-01-20","lifecycle":null,"limits":{"context":163840,"output":163840},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-R1","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"deepseek-r1-0528":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"forced_choice":false}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"deepseek-r1-0528","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"deepseek-v3-0324":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"forced_choice":false}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"deepseek-v3-0324","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"deepseek-v3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"forced_choice":false}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"deepseek-v3.1","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"deepseek-v3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.58,"output":1.68},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"reasoning_options":[],"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"deepseek-v3.2","knowledge":"2024-07","last_updated":"2025-12-01","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3.2","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"deepseek-v3.2-speciale":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.58,"output":1.68},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"reasoning_options":[],"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"deepseek-v3.2-speciale","knowledge":"2024-07","last_updated":"2025-12-01","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3.2-Speciale","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"gpt-3.5-turbo-0125":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"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,"status":"deprecated","temperature":true},"family":null,"id":"gpt-3.5-turbo-0125","knowledge":"2021-08","last_updated":"2024-01-25","lifecycle":null,"limits":{"context":16384,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-3.5 Turbo 0125","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"gpt-3.5-turbo-1106":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"status":"deprecated","temperature":true},"family":null,"id":"gpt-3.5-turbo-1106","knowledge":"2021-08","last_updated":"2023-11-06","lifecycle":null,"limits":{"context":16384,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-3.5 Turbo 1106","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"gpt-3.5-turbo-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1.5,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"status":"deprecated","temperature":true},"family":null,"id":"gpt-3.5-turbo-instruct","knowledge":"2021-08","last_updated":"2023-09-21","lifecycle":null,"limits":{"context":4096,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-3.5 Turbo Instruct","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2023-09-21","retired":false,"tags":null},"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,"status":"deprecated","temperature":true},"family":null,"id":"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":"azure_cognitive_services","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"gpt-4-turbo-vision":{"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,"status":"deprecated","temperature":true},"family":null,"id":"gpt-4-turbo-vision","knowledge":"2023-11","last_updated":"2024-04-09","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4 Turbo Vision","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"gpt-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","open_weights":false,"status":"deprecated","temperature":true,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-4.1","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.4,"output":1.6},"deprecated":false,"extra":{"attachment":true,"description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","open_weights":false,"status":"deprecated","temperature":true,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-4.1-mini","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1 mini","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.1,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","open_weights":false,"status":"deprecated","temperature":true,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-4.1-nano","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1 nano","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4o":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","open_weights":false,"status":"deprecated","temperature":true,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-4o","knowledge":"2023-09","last_updated":"2024-08-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"gpt-4o-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","open_weights":false,"status":"deprecated","temperature":true,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-4o-mini","knowledge":"2023-09","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o mini","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"gpt-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"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":["minimal","low","medium","high"]}],"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5","knowledge":"2024-09-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"input":1.25,"output":10},"deprecated":false,"extra":{"api":"responses","attachment":false,"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"]}],"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5-codex","knowledge":"2024-09-30","last_updated":"2025-09-15","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5-Codex","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-09-15","retired":false,"tags":null},"gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5-mini","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Mini","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.05,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5-nano","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Nano","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-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":{"input":15,"output":120},"deprecated":false,"extra":{"attachment":true,"description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["high"]}],"structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5-pro","knowledge":"2024-09-30","last_updated":"2025-10-06","lifecycle":null,"limits":{"context":400000,"output":272000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Pro","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-10-06","retired":false,"tags":null},"gpt-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5.1","knowledge":"2024-09-30","last_updated":"2025-11-14","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","audio"],"output":["text","image","audio"]},"model":null,"name":"GPT-5.1","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-11-14","retired":false,"tags":null},"gpt-5.1-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"api":"responses","attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5.1-codex","knowledge":"2024-09-30","last_updated":"2025-11-14","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","audio"],"output":["text","image","audio"]},"model":null,"name":"GPT-5.1 Codex","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-11-14","retired":false,"tags":null},"gpt-5.1-codex-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":2},"deprecated":false,"extra":{"api":"responses","attachment":false,"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,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5.1-codex-mini","knowledge":"2024-09-30","last_updated":"2025-11-14","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex Mini","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-11-14","retired":false,"tags":null},"gpt-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"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"]}],"structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5.2","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"gpt-5.2-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":false,"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","xhigh"]}],"structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5.2-codex","knowledge":"2025-08-31","last_updated":"2026-01-14","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2 Codex","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-01-14","retired":false,"tags":null},"gpt-5.3-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":false,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5.3-codex","knowledge":"2025-08-31","last_updated":"2026-02-24","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.3 Codex","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-02-24","retired":false,"tags":null},"gpt-5.4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"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":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"gpt-5.4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.75,"output":4.5},"deprecated":false,"extra":{"attachment":true,"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5.4-mini","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.4 Mini","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"gpt-5.4-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.2,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5.4-nano","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.4 Nano","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"gpt-5.4-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":30,"output":180},"deprecated":false,"extra":{"attachment":true,"description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":false,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5.4-pro","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 Pro","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"gpt-5.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"gpt-5.6-luna":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":1.25,"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","xhigh","max"]}],"status":"beta","structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"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":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5.6-sol":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"status":"beta","structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"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":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5.6-terra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"cache_write":3.125,"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","xhigh","max"]}],"status":"beta","structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"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":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"beta","structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-chat-latest","knowledge":"2025-12-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT Chat Latest","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-05-05","retired":false,"tags":null},"kimi-k2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","interleaved":true,"open_weights":true,"provider":{"api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/models","npm":"@ai-sdk/openai-compatible","shape":"completions"},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"kimi-k2.5","knowledge":"2025-01","last_updated":"2026-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"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":false,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":true,"open_weights":true,"provider":{"api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/models","npm":"@ai-sdk/openai-compatible","shape":"completions"},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"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":"azure_cognitive_services","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"llama-3.3-70b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.71,"output":0.71},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"llama-3.3-70b-instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"llama-4-maverick-17b-128e-instruct-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":1},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","open_weights":true,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"llama-4-maverick-17b-128e-instruct-fp8","knowledge":"2024-08","last_updated":"2025-04-05","lifecycle":null,"limits":{"context":1000000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Maverick 17B 128E Instruct FP8","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"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}},"catalog_only":true,"cost":{"input":0.2,"output":0.78},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","open_weights":true,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"llama-4-scout-17b-16e-instruct","knowledge":"2024-08","last_updated":"2025-04-05","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Scout 17B 16E Instruct","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"ministral-3b":{"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":0.04,"output":0.04},"deprecated":false,"extra":{"attachment":false,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"ministral-3b","knowledge":"2024-03","last_updated":"2024-10-22","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Ministral 3B","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-10-22","retired":false,"tags":null},"mistral-medium-2505":{"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":0.4,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","open_weights":false,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"mistral-medium-2505","knowledge":"2025-05","last_updated":"2025-05-07","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Medium 3","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-05-07","retired":false,"tags":null},"mistral-small-2503":{"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":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":false,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"mistral-small-2503","knowledge":"2024-09","last_updated":"2025-03-01","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 3.1","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-03-01","retired":false,"tags":null},"model-router":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"model-router","open_weights":false},"family":null,"id":"model-router","knowledge":null,"last_updated":"2025-11-18","lifecycle":null,"limits":{"context":200000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Model Router","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-05-19","retired":false,"tags":null},"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":false,"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"]}],"status":"deprecated","temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"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":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"o3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"o3","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o3","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"o3-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"deprecated","temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"o3-mini","knowledge":"2024-05","last_updated":"2025-01-29","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"o3-mini","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-12-20","retired":false,"tags":null},"o4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.275,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"deprecated","temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"o4-mini","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o4-mini","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"phi-4":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.125,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"phi","open_weights":true,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"phi-4","knowledge":"2023-10","last_updated":"2024-12-11","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Phi-4","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-12-11","retired":false,"tags":null},"phi-4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.075,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"phi","open_weights":true,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"phi-4-mini","knowledge":"2023-10","last_updated":"2024-12-11","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Phi-4-mini","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-12-11","retired":false,"tags":null},"phi-4-mini-reasoning":{"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":0.075,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"phi","open_weights":true,"reasoning_options":[],"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"phi-4-mini-reasoning","knowledge":"2023-10","last_updated":"2024-12-11","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Phi-4-mini-reasoning","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-12-11","retired":false,"tags":null},"phi-4-multimodal":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.08,"input_audio":4,"output":0.32},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"phi","open_weights":true,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"phi-4-multimodal","knowledge":"2023-10","last_updated":"2024-12-11","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Phi-4-multimodal","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-12-11","retired":false,"tags":null},"phi-4-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.125,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"phi","open_weights":true,"reasoning_options":[],"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"phi-4-reasoning","knowledge":"2023-10","last_updated":"2024-12-11","lifecycle":null,"limits":{"context":32000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Phi-4-reasoning","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-12-11","retired":false,"tags":null},"phi-4-reasoning-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.125,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"phi","open_weights":true,"reasoning_options":[],"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"phi-4-reasoning-plus","knowledge":"2023-10","last_updated":"2024-12-11","lifecycle":null,"limits":{"context":32000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Phi-4-reasoning-plus","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-12-11","retired":false,"tags":null},"text-embedding-3-large":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":3072,"max_dimensions":3072,"min_dimensions":1},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.13,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":false,"type":"embedding"},"family":null,"id":"text-embedding-3-large","knowledge":null,"last_updated":"2024-01-25","lifecycle":null,"limits":{"context":8191,"output":3072},"modalities":{"input":["text"],"output":["text","embedding"]},"model":null,"name":"text-embedding-3-large","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"text-embedding-3-small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1536,"max_dimensions":1536,"min_dimensions":1},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.02,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":false,"type":"embedding"},"family":null,"id":"text-embedding-3-small","knowledge":null,"last_updated":"2024-01-25","lifecycle":null,"limits":{"context":8191,"output":1536},"modalities":{"input":["text"],"output":["text","embedding"]},"model":null,"name":"text-embedding-3-small","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"text-embedding-ada-002":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1536,"max_dimensions":1536,"min_dimensions":1536},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.1,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":false,"type":"embedding"},"family":null,"id":"text-embedding-ada-002","knowledge":null,"last_updated":"2022-12-15","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text","embedding"]},"model":null,"name":"text-embedding-ada-002","pricing":null,"provider":"azure_cognitive_services","provider_model_id":null,"release_date":"2022-12-15","retired":false,"tags":null}},"name":"Azure Cognitive Services","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/bailing.d.ts

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

package/dist/providers/bailing.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.tbox.cn/api/llm/v1/chat/completions","catalog_only":true,"config_schema":null,"doc":"https://alipaytbox.yuque.com/sxs0ba/ling/intro","env":["BAILING_API_TOKEN"],"exclude_models":null,"extra":null,"id":"bailing","models":{"Ling-1T":{"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":0.57,"output":2.29},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"ling","open_weights":true,"temperature":true},"family":null,"id":"Ling-1T","knowledge":"2024-06","last_updated":"2025-10","lifecycle":null,"limits":{"context":128000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Ling-1T","pricing":null,"provider":"bailing","provider_model_id":null,"release_date":"2025-10","retired":false,"tags":null},"Ring-1T":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.57,"output":2.29},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ring","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"Ring-1T","knowledge":"2024-06","last_updated":"2025-10","lifecycle":null,"limits":{"context":128000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Ring-1T","pricing":null,"provider":"bailing","provider_model_id":null,"release_date":"2025-10","retired":false,"tags":null}},"name":"Bailing","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/baseten.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "baseten",
+  "MiniMaxAI/MiniMax-M2.5" | "deepseek-ai/DeepSeek-V3.1" | "deepseek-ai/DeepSeek-V4-Flash-0731" | "deepseek-ai/DeepSeek-V4-Pro" | "moonshotai/Kimi-K2.5" | "moonshotai/Kimi-K2.6" | "moonshotai/Kimi-K2.7-Code" | "moonshotai/Kimi-K3" | "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B" | "nvidia/Nemotron-120B-A12B" | "openai/gpt-oss-120b" | "thinkingmachines/inkling" | "thinkingmachines/inkling-small" | "zai-org/GLM-4.7" | "zai-org/GLM-5" | "zai-org/GLM-5.1" | "zai-org/GLM-5.2" | "zai-org/GLM-5.2-Fast"
+>;
+export default provider;

package/dist/providers/baseten.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://inference.baseten.co/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.baseten.co/inference/model-apis/overview","env":["BASETEN_API_KEY"],"exclude_models":null,"extra":null,"id":"baseten","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":"Legacy model retained for compatibility with older integrations","family":"minimax","interleaved":{"field":"reasoning_content"},"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":[],"status":"deprecated","temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5","knowledge":"2026-01","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204000,"output":204000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":273040,"hf_likes":825,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3.1","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-08-21","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"status":"deprecated","temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.1","knowledge":null,"last_updated":"2025-08-25","lifecycle":null,"limits":{"context":164000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.1","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2025-08-25","retired":false,"tags":null},"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}},"catalog_only":true,"cost":{"cache_read":0.028,"input":0.13,"output":0.26},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":236076,"hf_likes":1963,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","memory":{"min_ram_gb":170.0,"min_vram_gb":155.8,"recommended_ram_gb":283.3},"model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","moe":{"active_experts":6,"active_parameters":21981788050,"is_moe":true,"num_experts":256},"parameter_count":"304.2B","parameters_raw":304180418494,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-07-31","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek V4 Flash 0731","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.145,"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","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":1596582,"hf_likes":5373,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","memory":{"min_ram_gb":893.4,"min_vram_gb":819.0,"recommended_ram_gb":1489.0},"model_id":"deepseek-ai/DeepSeek-V4-Pro","moe":{"active_experts":6,"active_parameters":49000000000,"is_moe":true,"num_experts":384},"parameter_count":"1598.8B","parameters_raw":1598839674782,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek V4 Pro","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"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":0.12,"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"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Kimi-K2.5-GGUF"}],"hf_downloads":967470,"hf_likes":2860,"matched_hugging_face_id":"moonshotai/Kimi-K2.5","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.5","moe":{"active_experts":8,"active_parameters":32000000000,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2026-01-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5","knowledge":"2025-12","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-01-30","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"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"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K2.7-Code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":695030,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.7-Code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshotai/Kimi-K3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","llmfit":{"architecture":"kimi_k3","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":967622,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K3","memory":{"min_ram_gb":1553.4,"min_vram_gb":1424.0,"recommended_ram_gb":2589.0},"model_id":"moonshotai/Kimi-K3","parameter_count":"2779.9B","parameters_raw":2779931837184,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B":{"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":0.12,"input":0.6,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":202800,"output":202800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron Ultra","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"nvidia/Nemotron-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":{"cache_read":0.06,"input":0.3,"output":0.75},"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"}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/Nemotron-120B-A12B","knowledge":"2026-02","last_updated":"2026-03-11","lifecycle":null,"limits":{"context":202800,"output":202800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron Super","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","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":"2025-08","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128072,"output":128072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI GPT 120B","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"thinkingmachines/inkling":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":4.05},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"thinkingmachines/inkling","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":1048576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"thinkingmachines/inkling-small":{"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":0.5,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"thinkingmachines/inkling-small","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":1048576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Inkling Small","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-07-30","retired":false,"tags":null},"zai-org/GLM-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12,"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.7-GGUF"}],"hf_downloads":72466,"hf_likes":2051,"matched_hugging_face_id":"zai-org/GLM-4.7","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.7","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-12-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":200000,"output":200000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"zai-org/GLM-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":0.95,"output":3.15},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5-GGUF"}],"hf_downloads":155600,"hf_likes":2119,"matched_hugging_face_id":"zai-org/GLM-5","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5","moe":{"active_experts":8,"active_parameters":40000000000,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-02-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5","knowledge":"2026-01","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":202800,"output":202800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"zai-org/GLM-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.3,"output":4.3},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5.1-GGUF"}],"hf_downloads":76699,"hf_likes":1840,"matched_hugging_face_id":"zai-org/GLM-5.1","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1","moe":{"active_experts":8,"active_parameters":60073548574,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202800,"output":202800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"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","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2180509,"hf_likes":4785,"matched_hugging_face_id":"zai-org/GLM-5.2","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2","moe":{"active_experts":8,"active_parameters":60030979632,"is_moe":true,"num_experts":256},"parameter_count":"753.3B","parameters_raw":753329940480,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-06-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"zai-org/GLM-5.2-Fast":{"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":0.21,"input":2.1,"output":6.6},"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-Fast","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":524288,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 Fast","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Baseten","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/berget.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "berget",
+  "google/gemma-4-31B-it" | "meta-llama/Llama-3.3-70B-Instruct" | "mistralai/Mistral-Medium-3.5-128B" | "mistralai/Mistral-Small-3.2-24B-Instruct-2506" | "moonshotai/Kimi-K2.6" | "moonshotai/Kimi-K3" | "openai/gpt-oss-120b" | "zai-org/GLM-4.7" | "zai-org/GLM-5.2"
+>;
+export default provider;

package/dist/providers/berget.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.berget.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://api.berget.ai","env":["BERGET_API_KEY"],"exclude_models":null,"extra":null,"id":"berget","models":{"google/gemma-4-31B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.275,"output":0.55},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-31B-it-GGUF"}],"hf_downloads":11886065,"hf_likes":3433,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":18.3,"min_vram_gb":16.7,"recommended_ram_gb":30.4},"model_id":"google/gemma-4-31B-it","parameter_count":"32.7B","parameters_raw":32682372656,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-it","knowledge":"2025-12","last_updated":"2026-04-02","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["audio","image","text","video"],"output":["text"]},"model":null,"name":"Gemma 4 31B Instruct","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-04-02","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":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.99,"output":0.99},"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,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/Llama-3.3-70B-Instruct","knowledge":"2023-12","last_updated":"2025-04-27","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2025-04-27","retired":false,"tags":null},"mistralai/Mistral-Medium-3.5-128B":{"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":1.65,"output":5.5},"deprecated":false,"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"mistralai/Mistral-Medium-3.5-128B","knowledge":"2026-04","last_updated":"2026-04-29","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"Mistral Medium 3.5 128B","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-04-29","retired":false,"tags":null},"mistralai/Mistral-Small-3.2-24B-Instruct-2506":{"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":0.33,"output":0.33},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","knowledge":"2025-09","last_updated":"2025-10-01","lifecycle":null,"limits":{"context":32000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Small 3.2 24B Instruct 2506","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2025-10-01","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"input":0.83,"output":3.85},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-05-07","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":{"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"},"llmfit":{"architecture":"kimi_k3","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":967622,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K3","memory":{"min_ram_gb":1553.4,"min_vram_gb":1424.0,"recommended_ram_gb":2589.0},"model_id":"moonshotai/Kimi-K3","parameter_count":"2779.9B","parameters_raw":2779931837184,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/Kimi-K3","knowledge":null,"last_updated":"2026-07-28","lifecycle":null,"limits":{"context":327680,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.22,"output":0.83},"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":"2025-08","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-OSS-120B","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"zai-org/GLM-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.77,"output":2.75},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.7-GGUF"}],"hf_downloads":72466,"hf_likes":2051,"matched_hugging_face_id":"zai-org/GLM-4.7","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.7","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-12-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.7","knowledge":"2025-12","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.54,"output":4.84},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","llmfit":{"architecture":"glm_moe_dsa","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2180509,"hf_likes":4785,"matched_hugging_face_id":"zai-org/GLM-5.2","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2","moe":{"active_experts":8,"active_parameters":60030979632,"is_moe":true,"num_experts":256},"parameter_count":"753.3B","parameters_raw":753329940480,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-06-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":524288,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Berget.AI","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/blueclaw.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "blueclaw",
+  "Qwen/Qwen3.6-35B-A3B-FP8" | "Qwen3.6-27B"
+>;
+export default provider;

package/dist/providers/blueclaw.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://openai.blueclaw.network/v1","catalog_only":true,"config_schema":null,"doc":"https://blueclaw.network","env":["BLUECLAW_API_KEY"],"exclude_models":null,"extra":null,"id":"blueclaw","models":{"Qwen/Qwen3.6-35B-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}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":8818827,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3.6-35B-A3B-FP8","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.6-35B-A3B-FP8","moe":{"active_experts":8,"active_parameters":2865078437,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35953925552,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-35B-A3B-FP8","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 35B A3B FP8","pricing":null,"provider":"blueclaw","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"Qwen3.6-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"Qwen3.6-27B","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":196608,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"blueclaw","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null}},"name":"Blue Claw","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/cerebras.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "cerebras",
+  "gemma-4-31b" | "gpt-oss-120b" | "qwen-3-235b-a22b-instruct-2507" | "qwen-3-coder-480b" | "zai-glm-4.7"
+>;
+export default provider;

package/dist/providers/cerebras.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.cerebras.ai/v1","config_schema":null,"doc":"https://cerebras.ai/docs","env":["CEREBRAS_API_KEY"],"exclude_models":["qwen-3-235b-a22b-thinking-2507"],"extra":null,"id":"cerebras","models":{"gemma-4-31b":{"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":0.99,"output":1.49},"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":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"gemma-4-31b","knowledge":null,"last_updated":"2026-07-01","lifecycle":null,"limits":{"context":131072,"output":40960},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"cerebras","provider_model_id":null,"release_date":"2026-04-02","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,"strict":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":"gpt-oss-120b","knowledge":null,"last_updated":"2026-06-10","lifecycle":null,"limits":{"context":131072,"output":40960},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"cerebras","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"qwen-3-235b-a22b-instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"strict":false}},"cost":null,"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":null,"family":null,"id":"qwen-3-235b-a22b-instruct-2507","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"cerebras","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"qwen-3-coder-480b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"strict":false}},"cost":null,"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":null,"family":null,"id":"qwen-3-coder-480b","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"cerebras","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"zai-glm-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":2.25,"cache_write":0,"input":2.25,"output":2.75},"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":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","open_weights":true,"reasoning_options":[{"type":"effort","values":["none"]}],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"zai-glm-4.7","knowledge":null,"last_updated":"2026-06-10","lifecycle":null,"limits":{"context":131072,"output":40960},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Z.AI GLM-4.7","pricing":null,"provider":"cerebras","provider_model_id":null,"release_date":"2026-01-07","retired":false,"tags":null}},"name":"Cerebras","pricing_defaults":null,"runtime":{"auth":{"env":["CEREBRAS_API_KEY"],"headers":[],"type":"bearer"},"base_url":"https://api.cerebras.ai/v1","config_schema":null,"default_headers":{},"default_query":{},"doc_url":"https://cerebras.ai/docs"}};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/chutes.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "chutes",
+  "Nemotron-3-Nano-Omni-30B-TEE" | "Qwen/Qwen3-235B-A22B-Thinking-2507-TEE" | "Qwen/Qwen3-32B-TEE" | "Qwen/Qwen3.5-397B-A17B-TEE" | "Qwen/Qwen3.6-27B-TEE" | "deepseek-ai/DeepSeek-V3.2-TEE" | "deepseek-ai/DeepSeek-V4-Flash-0731-TEE" | "google/gemma-4-31B-turbo-TEE" | "moonshotai/Kimi-K2.6-TEE" | "moonshotai/Kimi-K3-TEE" | "unsloth/Mistral-Nemo-Instruct-2407-TEE" | "zai-org/GLM-5.1-TEE" | "zai-org/GLM-5.2-TEE"
+>;
+export default provider;