@agentjido/llmdb 2026.8.2

package/dist/providers/azure.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_RESOURCE_NAME","AZURE_API_KEY"],"exclude_models":null,"extra":null,"id":"azure","models":{"claude-fable-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","open_weights":false,"provider":{"api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1","npm":"@ai-sdk/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false,"wire_protocol":"anthropic_messages"},"family":null,"id":"claude-fable-5","knowledge":"2026-01-31","last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Fable 5","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"claude-haiku-4-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"provider":{"api":"https://${AZURE_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","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://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1","npm":"@ai-sdk/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":true,"wire_protocol":"anthropic_messages"},"family":null,"id":"claude-opus-4-1","knowledge":"2025-03-31","last_updated":"2025-11-18","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.1","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"claude-opus-4-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"provider":{"api":"https://${AZURE_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","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://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1","npm":"@ai-sdk/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"min":1024,"type":"budget_tokens"}],"temperature":true,"wire_protocol":"anthropic_messages"},"family":null,"id":"claude-opus-4-6","knowledge":"2025-05-31","last_updated":"2026-07-17","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.6","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"claude-opus-4-8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"provider":{"api":"https://${AZURE_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","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://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1","npm":"@ai-sdk/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false,"wire_protocol":"anthropic_messages"},"family":null,"id":"claude-opus-5","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"claude-sonnet-4-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"provider":{"api":"https://${AZURE_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","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"claude-sonnet-4-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","open_weights":false,"provider":{"api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1","npm":"@ai-sdk/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":true,"wire_protocol":"anthropic_messages"},"family":null,"id":"claude-sonnet-4-6","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"claude-sonnet-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"provider":{"api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1","npm":"@ai-sdk/anthropic"},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"status":"beta","structured_output":true,"temperature":false,"wire_protocol":"anthropic_messages"},"family":null,"id":"claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2026-06-30","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","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","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","provider_model_id":null,"release_date":"2025-03-13","retired":false,"tags":null},"cohere-command-r-08-2024":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"cohere-command-r-08-2024","knowledge":null,"last_updated":null,"lifecycle":{"retires_at":"2026-05-12","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"cohere-command-r-plus-08-2024":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"cohere-command-r-plus-08-2024","knowledge":null,"last_updated":null,"lifecycle":{"retires_at":"2026-05-12","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"cohere-embed-v-4-0":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"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","provider_model_id":null,"release_date":"2025-04-15","retired":false,"tags":null},"cohere-embed-v3-english":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"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","provider_model_id":null,"release_date":"2023-11-07","retired":false,"tags":null},"cohere-embed-v3-multilingual":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"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","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","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","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","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","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","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","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"deepseek-v4-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":true},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.19,"output":0.51},"deprecated":false,"extra":{"attachment":true,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-v4","interleaved":{"field":"reasoning_content"},"open_weights":true,"provider":{"api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","npm":"@ai-sdk/openai-compatible","shape":"completions"},"reasoning_options":[],"structured_output":true,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-04-28","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V4-Flash","pricing":{"components":[{"id":"token.input","kind":"token","per":1000000,"rate":0.19,"unit":"token"},{"id":"token.output","kind":"token","per":1000000,"rate":0.51,"unit":"token"}],"currency":"USD","merge":"merge_by_id"},"provider":"azure","provider_model_id":null,"release_date":"2026-04-28","retired":false,"tags":null},"deepseek-v4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":true},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.74,"output":3.48},"deprecated":false,"extra":{"attachment":true,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-v4","interleaved":{"field":"reasoning_content"},"open_weights":true,"provider":{"api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","npm":"@ai-sdk/openai-compatible","shape":"completions"},"reasoning_options":[],"structured_output":true,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-28","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V4-Pro","pricing":{"components":[{"id":"token.input","kind":"token","per":1000000,"rate":1.74,"unit":"token"},{"id":"token.output","kind":"token","per":1000000,"rate":3.48,"unit":"token"}],"currency":"USD","merge":"merge_by_id"},"provider":"azure","provider_model_id":null,"release_date":"2026-04-28","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","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","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","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","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","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","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","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","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","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","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","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","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","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","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","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","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","provider_model_id":null,"release_date":"2025-11-14","retired":false,"tags":null},"gpt-5.1-codex-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false,"wire_protocol":"openai_responses"},"family":null,"id":"gpt-5.1-codex-max","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex Max","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2025-11-13","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","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","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","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","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","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","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","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","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","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","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","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","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","provider_model_id":null,"release_date":"2026-05-05","retired":false,"tags":null},"gpt-image-1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":1.25,"input":5,"output":40},"deprecated":false,"extra":{"attachment":true,"description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","family":"gpt-image","open_weights":false,"temperature":false},"family":null,"id":"gpt-image-1","knowledge":null,"last_updated":"2025-04-24","lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"GPT-Image-1","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2025-04-24","retired":false,"tags":null},"gpt-image-1.5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":1.25,"input":5,"output":32},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","open_weights":false,"temperature":false},"family":null,"id":"gpt-image-1.5","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"GPT-Image-1.5","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2025-11-25","retired":false,"tags":null},"gpt-image-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":1.25,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","open_weights":false,"temperature":false},"family":null,"id":"gpt-image-2","knowledge":null,"last_updated":"2026-04-21","lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"GPT-Image-2","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"grok-4-1-fast-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.2,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"status":"beta","temperature":true,"wire_protocol":"openai_responses"},"family":null,"id":"grok-4-1-fast-non-reasoning","knowledge":null,"last_updated":"2025-06-27","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.1 Fast (Non-Reasoning)","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2025-06-27","retired":false,"tags":null},"grok-4-1-fast-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":{"cache_read":0.05,"input":0.2,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"reasoning_options":[],"status":"beta","temperature":true,"wire_protocol":"openai_responses"},"family":null,"id":"grok-4-1-fast-reasoning","knowledge":null,"last_updated":"2025-06-27","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.1 Fast (Reasoning)","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2025-06-27","retired":false,"tags":null},"grok-4-20-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"status":"beta","temperature":true,"wire_protocol":"openai_responses"},"family":null,"id":"grok-4-20-non-reasoning","knowledge":"2025-09","last_updated":"2026-04-08","lifecycle":null,"limits":{"context":262000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Grok 4.20 (Non-Reasoning)","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2026-04-08","retired":false,"tags":null},"grok-4-20-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":2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[],"status":"beta","temperature":true,"wire_protocol":"openai_responses"},"family":null,"id":"grok-4-20-reasoning","knowledge":"2025-09","last_updated":"2026-04-08","lifecycle":null,"limits":{"context":262000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Grok 4.20 (Reasoning)","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2026-04-08","retired":false,"tags":null},"grok-4-fast-reasoning":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_responses"},"family":null,"id":"grok-4-fast-reasoning","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"grok-4-1-fast-reasoning","retires_at":"2026-05-01","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"kimi-k2-thinking":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"kimi-k2-thinking","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"kimi-k2.5","retires_at":"2026-03-29","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"kimi-k2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":true,"open_weights":true,"provider":{"api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","npm":"@ai-sdk/openai-compatible","shape":"completions"},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true,"wire_protocol":"openai_completion"},"family":null,"id":"kimi-k2.5","knowledge":"2025-01","last_updated":"2026-02-06","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2026-02-06","retired":false,"tags":null},"kimi-k2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":false,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":true,"open_weights":true,"provider":{"api":"https://${AZURE_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":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"llama-3.2-11b-vision-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"llama-3.2-11b-vision-instruct","knowledge":null,"last_updated":null,"lifecycle":{"retires_at":"2026-06-13","status":"deprecated"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"llama-3.2-90b-vision-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"llama-3.2-90b-vision-instruct","knowledge":null,"last_updated":null,"lifecycle":{"retires_at":"2026-06-13","status":"deprecated"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"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","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","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","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"mai-ds-r1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"mai-ds-r1","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"Any DeepSeek model available in the Model catalog","retires_at":"2026-02-27","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"meta-llama-3-70b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"meta-llama-3-70b-instruct","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"llama-3.3-70b-instruct","retires_at":"2025-06-30","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"meta-llama-3-8b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"meta-llama-3-8b-instruct","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"meta-llama-3.1-8b-instruct","retires_at":"2025-06-30","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"meta-llama-3.1-405b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"meta-llama-3.1-405b-instruct","knowledge":null,"last_updated":null,"lifecycle":{"retires_at":"2026-06-13","status":"deprecated"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"meta-llama-3.1-70b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"meta-llama-3.1-70b-instruct","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"llama-3.3-70b-instruct","retires_at":"2025-06-30","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"meta-llama-3.1-8b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"meta-llama-3.1-8b-instruct","knowledge":null,"last_updated":null,"lifecycle":{"retires_at":"2026-06-13","status":"deprecated"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"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","provider_model_id":null,"release_date":"2024-10-22","retired":false,"tags":null},"mistral-large-2411":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"mistral-large-2411","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"mistral-medium-2505","retires_at":"2026-01-30","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"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","provider_model_id":null,"release_date":"2025-05-07","retired":false,"tags":null},"mistral-nemo":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"mistral-nemo","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"mistral-small-2503","retires_at":"2026-01-30","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"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","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","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":true,"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":{"retires_at":"2026-07-15","status":"deprecated"},"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o1","pricing":null,"provider":"azure","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"o1-preview":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_responses"},"family":null,"id":"o1-preview","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"o1","retires_at":"2025-07-28","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"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","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":true,"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":{"replacement":"o4-mini","retires_at":"2026-08-02","status":"deprecated"},"limits":{"context":200000,"output":100000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"o3-mini","pricing":null,"provider":"azure","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","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"phi-3-medium-128k-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"phi-3-medium-128k-instruct","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"phi-4","retires_at":"2025-08-30","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"phi-3-medium-4k-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"phi-3-medium-4k-instruct","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"phi-4","retires_at":"2025-08-30","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"phi-3-mini-128k-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"phi-3-mini-128k-instruct","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"phi-4-mini","retires_at":"2025-08-30","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"phi-3-mini-4k-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"phi-3-mini-4k-instruct","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"phi-4-mini","retires_at":"2025-08-30","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"phi-3-small-128k-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"phi-3-small-128k-instruct","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"phi-4-mini","retires_at":"2025-08-30","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"phi-3-small-8k-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"phi-3-small-8k-instruct","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"phi-4-mini","retires_at":"2025-08-30","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"phi-3.5-mini-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"phi-3.5-mini-instruct","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"phi-4-mini","retires_at":"2025-08-30","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"tags":null},"phi-3.5-moe-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":{"wire_protocol":"openai_completion"},"family":null,"id":"phi-3.5-moe-instruct","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"phi-4-mini","retires_at":"2025-08-30","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"azure","provider_model_id":null,"release_date":null,"retired":true,"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","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","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","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","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","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","provider_model_id":null,"release_date":"2024-12-11","retired":false,"tags":null},"text-embedding-3-large":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"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","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"text-embedding-3-small":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"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","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"text-embedding-ada-002":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"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","provider_model_id":null,"release_date":"2022-12-15","retired":false,"tags":null}},"name":"Azure","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/azure_cognitive_services.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "azure_cognitive_services",
+  "claude-haiku-4-5" | "claude-opus-4-1" | "claude-opus-4-5" | "claude-opus-4-6" | "claude-opus-4-8" | "claude-opus-5" | "claude-sonnet-4-5" | "codestral-2501" | "codex-mini" | "cohere-command-a" | "cohere-embed-v-4-0" | "cohere-embed-v3-english" | "cohere-embed-v3-multilingual" | "deepseek-r1" | "deepseek-r1-0528" | "deepseek-v3-0324" | "deepseek-v3.1" | "deepseek-v3.2" | "deepseek-v3.2-speciale" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-instruct" | "gpt-4-turbo" | "gpt-4-turbo-vision" | "gpt-4.1" | "gpt-4.1-mini" | "gpt-4.1-nano" | "gpt-4o" | "gpt-4o-mini" | "gpt-5" | "gpt-5-codex" | "gpt-5-mini" | "gpt-5-nano" | "gpt-5-pro" | "gpt-5.1" | "gpt-5.1-codex" | "gpt-5.1-codex-mini" | "gpt-5.2" | "gpt-5.2-codex" | "gpt-5.3-codex" | "gpt-5.4" | "gpt-5.4-mini" | "gpt-5.4-nano" | "gpt-5.4-pro" | "gpt-5.5" | "gpt-5.6-luna" | "gpt-5.6-sol" | "gpt-5.6-terra" | "gpt-chat-latest" | "kimi-k2.5" | "kimi-k2.6" | "llama-3.3-70b-instruct" | "llama-4-maverick-17b-128e-instruct-fp8" | "llama-4-scout-17b-16e-instruct" | "ministral-3b" | "mistral-medium-2505" | "mistral-small-2503" | "model-router" | "o1" | "o3" | "o3-mini" | "o4-mini" | "phi-4" | "phi-4-mini" | "phi-4-mini-reasoning" | "phi-4-multimodal" | "phi-4-reasoning" | "phi-4-reasoning-plus" | "text-embedding-3-large" | "text-embedding-3-small" | "text-embedding-ada-002"
+>;
+export default provider;