MORPH
SIGN IN SIGN UP
BerriAI / litellm UNCLAIMED

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

0 0 1 Python
Normal View History Raw
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
{
"_comment": "This file defines which endpoints are supported by each LiteLLM provider",
"_schema": {
"provider_slug": {
"display_name": "Display name shown in README (e.g., 'OpenAI (`openai`)')",
"url": "Link to provider documentation",
"endpoints": {
"chat_completions": "Supports /chat/completions endpoint",
"messages": "Supports /messages endpoint (Anthropic format)",
"responses": "Supports /responses endpoint (OpenAI/Anthropic unified)",
"embeddings": "Supports /embeddings endpoint",
"image_generations": "Supports /image/generations endpoint",
"audio_transcriptions": "Supports /audio/transcriptions endpoint",
"audio_speech": "Supports /audio/speech endpoint",
"moderations": "Supports /moderations endpoint",
"batches": "Supports /batches endpoint",
[Feat] /ocr - Add VertexAI OCR provider support + cost tracking (#16216) * add VertexAIOCRConfig * __all__ = ["VertexAIOCRConfig"] add * add get_provider_ocr_config * use GenericLiteLLMParams for litellm params * fix _async_prepare_ocr_request * fix _prepare_ocr_request * fix get_complete_url * fix validate_environment * add safe_get_vertex_ai_project * add VertexAIOCRConfig * fix get_complete_url * add TestVertexAIOCR * add mistral-ocr-2505 cost * add OCR to provider info * docs vertex ai ocr * fix _handle_rate_limits * Potential fix for code scanning alert no. 3632: Clear-text logging of sensitive information Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> --------- Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2025-11-03 15:56:49 -08:00
"rerank": "Supports /rerank endpoint",
[Feat] /search API - add firecrawl search API support (#16257) * TestFirecrawlSearch * add SearchProviders * add to get_provider_search_config * add FirecrawlSearchConfig * add FirecrawlSearchRequest * add firecrawl API docs * add pricing firecrawl/search * add new search APIs
2025-11-04 17:52:12 -08:00
"ocr": "Supports /ocr endpoint",
[Docs] Claude Skills API (#17052) * add skillls api * init doc * docs fix * skills API
2025-11-24 15:32:03 -08:00
"search": "Supports /search endpoint",
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"skills": "Supports /skills endpoint",
docs init
2025-12-17 02:27:00 +04:00
"interactions": "Supports /interactions endpoint (Google AI Interactions API)",
[docs] add docs for containers files api + code interpreter on LiteLLM (#17749) * add new container api on OpenAI * add related * docs fix * docs code interpreter * code interp * docs code interptert * docs code int * docs code interp * docs code interp
2025-12-09 18:11:28 -08:00
"a2a_(Agent Gateway)": "Supports /a2a/{agent}/message/send endpoint (A2A Protocol)",
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
"container": "Supports OpenAI's /containers endpoint",
"container_file": "Supports OpenAI's /containers/{id}/files endpoint",
"compact": "Supports /responses/compact endpoint",
"files": "Supports /files endpoint for file operations",
"image_edits": "Supports /images/edits endpoint for image editing",
"vector_stores_create": "Supports creating a new vector store via /vector_stores endpoint",
"vector_stores_search": "Supports searching a vector store via /vector_stores/{id}/search endpoint",
"video_generations": "Supports /videos/generations endpoint for video generation"
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
}
},
"providers": {
feat: Add abliteration.ai provider (#18678) * feat: Add abliteration.ai provider * adding signoz integration to observability docs * Fixing build * Adding timeout for flaky test * Fixing e2e * add team member budget duration in team/update * Reusable Duration Select and update team member budget UI --------- Co-authored-by: Goutham Karthi <goutham@signoz.io> Co-authored-by: yuneng-jiang <yuneng.jiang@gmail.com> Co-authored-by: YutaSaito <36355491+uc4w6c@users.noreply.github.com>
2026-01-07 08:16:54 -08:00
"abliteration": {
"display_name": "Abliteration (`abliteration`)",
"url": "https://docs.litellm.ai/docs/providers/abliteration",
"endpoints": {
"chat_completions": true,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"a2a": false
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"aiml": {
"display_name": "AI/ML API (`aiml`)",
"url": "https://docs.litellm.ai/docs/providers/aiml",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": true,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"ai21": {
"display_name": "AI21 (`ai21`)",
"url": "https://docs.litellm.ai/docs/providers/ai21",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"ai21_chat": {
"display_name": "AI21 Chat (`ai21_chat`)",
"url": "https://docs.litellm.ai/docs/providers/ai21",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
Add Amazon Nova to sidebar and under supported models in README (#18220)
2025-12-19 05:37:34 -08:00
"amazon_nova": {
"display_name": "Amazon Nova (`amazon_nova`)",
"url": "https://docs.litellm.ai/docs/providers/amazon_nova",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
Add Amazon Nova to sidebar and under supported models in README (#18220)
2025-12-19 05:37:34 -08:00
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"anthropic": {
"display_name": "Anthropic (`anthropic`)",
"url": "https://docs.litellm.ai/docs/providers/anthropic",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": true,
[Docs] Claude Skills API (#17052) * add skillls api * init doc * docs fix * skills API
2025-11-24 15:32:03 -08:00
"rerank": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"skills": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
"interactions": true,
"count_tokens": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"anthropic_text": {
"display_name": "Anthropic Text (`anthropic_text`)",
"url": "https://docs.litellm.ai/docs/providers/anthropic",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": true,
[Docs] Claude Skills API (#17052) * add skillls api * init doc * docs fix * skills API
2025-11-24 15:32:03 -08:00
"rerank": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"skills": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
Add 5 AI providers using `openai_like` (#18362) * Add 5 AI providers using `openai_like`: * Synthetic.new * Apertis / Stima.tech * NanoGPT * Poe * Chutes.ai * Update additional missing locations
2025-12-23 02:05:54 -08:00
"apertis": {
"display_name": "Apertis (`apertis`)",
"endpoints": {
"chat_completions": true,
"messages": false,
"responses": false,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"a2a": false
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"assemblyai": {
"display_name": "AssemblyAI (`assemblyai`)",
"url": "https://docs.litellm.ai/docs/pass_through/assembly_ai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": true,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"auto_router": {
"display_name": "Auto Router (`auto_router`)",
"url": "https://docs.litellm.ai/docs/proxy/auto_routing",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"bedrock": {
"display_name": "AWS - Bedrock (`bedrock`)",
"url": "https://docs.litellm.ai/docs/providers/bedrock",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
"interactions": true,
"bedrock_invoke": true,
"bedrock_converse": true,
"vector_stores_search": true,
"count_tokens": true,
"rag_ingest": true,
"rag_query": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"sagemaker": {
"display_name": "AWS - Sagemaker (`sagemaker`)",
"url": "https://docs.litellm.ai/docs/providers/aws_sagemaker",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
[Feat] New provider TTS - Add AWS polly API for TTS (#18326) * add aws_polly as new provider * init AWSPollyTextToSpeechConfig * test_aws_polly_tts_with_native_voice * init aws_polly + AWS polly dispatch * init AWSPollyTextToSpeechConfig * fix transform * add aws_polly as a new provider for TTS API * add to sidebar * docs aws polly * code qa fix * add AWS Polly Text-to-Speech * add cost tracking for AWS polly * docs fix
2025-12-22 18:19:34 +05:30
"aws_polly": {
"display_name": "AWS - Polly (`aws_polly`)",
"url": "https://docs.litellm.ai/docs/providers/aws_polly",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": true,
"moderations": false,
"batches": false,
"rerank": false
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"azure": {
"display_name": "Azure (`azure`)",
"url": "https://docs.litellm.ai/docs/providers/azure",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": true,
"audio_transcriptions": true,
"audio_speech": true,
"moderations": true,
"batches": true,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
"interactions": true,
"vector_stores_search": true,
"assistants": true,
"fine_tuning": true,
"text_completion": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"azure_ai": {
"display_name": "Azure AI (`azure_ai`)",
"url": "https://docs.litellm.ai/docs/providers/azure_ai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": true,
[Feat] New provider - Add Azure BFL FLux for image edits (#18766) * add azure_ai/flux.2-pro * get_flux2_image_generation_url * azure_client_params * docs * add Image Editing * add azure ai image edits * AzureFoundryFlux2ImageEditConfig * TestAzureAIFlux2ImageEdit
2026-01-07 23:28:39 +05:30
"image_edits": true,
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"audio_transcriptions": true,
"audio_speech": true,
"moderations": true,
"batches": true,
[Feat] /ocr - Add VertexAI OCR provider support + cost tracking (#16216) * add VertexAIOCRConfig * __all__ = ["VertexAIOCRConfig"] add * add get_provider_ocr_config * use GenericLiteLLMParams for litellm params * fix _async_prepare_ocr_request * fix _prepare_ocr_request * fix get_complete_url * fix validate_environment * add safe_get_vertex_ai_project * add VertexAIOCRConfig * fix get_complete_url * add TestVertexAIOCR * add mistral-ocr-2505 cost * add OCR to provider info * docs vertex ai ocr * fix _handle_rate_limits * Potential fix for code scanning alert no. 3632: Clear-text logging of sensitive information Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> --------- Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2025-11-03 15:56:49 -08:00
"rerank": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"ocr": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
"interactions": true,
"vector_stores_create": true,
"vector_stores_search": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
[Feat] Add Azure AI Doc Intelligence OCR (#16219) * TestAzureDocumentIntelligenceOCR * add AZURE_DOCUMENT_INTELLIGENCE_API_VERSION * add AzureDocumentIntelligenceOCRConfig * add async_transform_ocr_response * use async transform * add AzureDocumentIntelligenceOCRConfig * add AzureDocumentIntelligenceOCRConfig * add AzureDocumentIntelligenceOCRConfig * add get_azure_ai_ocr_config * add azure_ai/doc-intelligence * add azure_ai/doc-intelligence * docs fix * docs fix * add azure doc intel * fix lint error
2025-11-03 17:22:19 -08:00
"azure_ai/doc-intelligence": {
"display_name": "Azure AI Document Intelligence (`azure_ai/doc-intelligence`)",
"url": "https://docs.litellm.ai/docs/providers/azure_document_intelligence",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"ocr": true
}
},
[Feat] New API Provider - Add Azure AI Foundry Agents on /chat/completions, /responses, /messages + Agent Gateway (#17845) * init get_azure_ai_route * init AzureAIAgentsConfig * init AzureAIAgentsConfig * AzureAIAgentsHandler * test_azure_ai_agents_acompletion_non_streaming * test_azure_ai_agents_acompletion_streaming * fix stream * _process_sse_stream * Azure AI Foundry Agents * init Azure AI Foundry Agent * fix code QA checks * fix api key * docs fix
2025-12-11 15:21:28 -08:00
"azure_ai/agents": {
"display_name": "Azure AI Foundry Agents (`azure_ai/agents`)",
"url": "https://docs.litellm.ai/docs/providers/azure_ai_agents",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Feat] New API Provider - Add Azure AI Foundry Agents on /chat/completions, /responses, /messages + Agent Gateway (#17845) * init get_azure_ai_route * init AzureAIAgentsConfig * init AzureAIAgentsConfig * AzureAIAgentsHandler * test_azure_ai_agents_acompletion_non_streaming * test_azure_ai_agents_acompletion_streaming * fix stream * _process_sse_stream * Azure AI Foundry Agents * init Azure AI Foundry Agent * fix code QA checks * fix api key * docs fix
2025-12-11 15:21:28 -08:00
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"azure_text": {
"display_name": "Azure Text (`azure_text`)",
"url": "https://docs.litellm.ai/docs/providers/azure",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": true,
"audio_speech": true,
"moderations": true,
"batches": true,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"baseten": {
"display_name": "Baseten (`baseten`)",
"url": "https://docs.litellm.ai/docs/providers/baseten",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"bytez": {
"display_name": "Bytez (`bytez`)",
"url": "https://docs.litellm.ai/docs/providers/bytez",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"cerebras": {
"display_name": "Cerebras (`cerebras`)",
"url": "https://docs.litellm.ai/docs/providers/cerebras",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
Add 5 AI providers using `openai_like` (#18362) * Add 5 AI providers using `openai_like`: * Synthetic.new * Apertis / Stima.tech * NanoGPT * Poe * Chutes.ai * Update additional missing locations
2025-12-23 02:05:54 -08:00
"chutes": {
"display_name": "Chutes (`chutes`)",
"endpoints": {
"chat_completions": true,
"messages": false,
"responses": false,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"a2a": false
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"clarifai": {
"display_name": "Clarifai (`clarifai`)",
"url": "https://docs.litellm.ai/docs/providers/clarifai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"cloudflare": {
"display_name": "Cloudflare AI Workers (`cloudflare`)",
"url": "https://docs.litellm.ai/docs/providers/cloudflare_workers",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"codestral": {
"display_name": "Codestral (`codestral`)",
"url": "https://docs.litellm.ai/docs/providers/codestral",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"cohere": {
"display_name": "Cohere (`cohere`)",
"url": "https://docs.litellm.ai/docs/providers/cohere",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"cohere_chat": {
"display_name": "Cohere Chat (`cohere_chat`)",
"url": "https://docs.litellm.ai/docs/providers/cohere",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"cometapi": {
"display_name": "CometAPI (`cometapi`)",
"url": "https://docs.litellm.ai/docs/providers/cometapi",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"compactifai": {
"display_name": "CompactifAI (`compactifai`)",
"url": "https://docs.litellm.ai/docs/providers/compactifai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"custom": {
"display_name": "Custom (`custom`)",
"url": "https://docs.litellm.ai/docs/providers/custom_llm_server",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"custom_openai": {
"display_name": "Custom OpenAI (`custom_openai`)",
"url": "https://docs.litellm.ai/docs/providers/openai_compatible",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": true,
"audio_speech": true,
"moderations": true,
"batches": true,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"dashscope": {
"display_name": "Dashscope (`dashscope`)",
"url": "https://docs.litellm.ai/docs/providers/dashscope",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"databricks": {
"display_name": "Databricks (`databricks`)",
"url": "https://docs.litellm.ai/docs/providers/databricks",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
[Feat] /search API - add firecrawl search API support (#16257) * TestFirecrawlSearch * add SearchProviders * add to get_provider_search_config * add FirecrawlSearchConfig * add FirecrawlSearchRequest * add firecrawl API docs * add pricing firecrawl/search * add new search APIs
2025-11-04 17:52:12 -08:00
"dataforseo": {
"display_name": "DataForSEO (`dataforseo`)",
"url": "https://docs.litellm.ai/docs/search/dataforseo",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"search": true
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"datarobot": {
"display_name": "DataRobot (`datarobot`)",
"url": "https://docs.litellm.ai/docs/providers/datarobot",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"deepgram": {
"display_name": "Deepgram (`deepgram`)",
"url": "https://docs.litellm.ai/docs/providers/deepgram",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": true,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"deepinfra": {
"display_name": "DeepInfra (`deepinfra`)",
"url": "https://docs.litellm.ai/docs/providers/deepinfra",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"deepseek": {
"display_name": "Deepseek (`deepseek`)",
"url": "https://docs.litellm.ai/docs/providers/deepseek",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"elevenlabs": {
"display_name": "ElevenLabs (`elevenlabs`)",
"url": "https://docs.litellm.ai/docs/providers/elevenlabs",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": true,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
[Feat] /search API - add firecrawl search API support (#16257) * TestFirecrawlSearch * add SearchProviders * add to get_provider_search_config * add FirecrawlSearchConfig * add FirecrawlSearchRequest * add firecrawl API docs * add pricing firecrawl/search * add new search APIs
2025-11-04 17:52:12 -08:00
"exa_ai": {
"display_name": "Exa AI (`exa_ai`)",
"url": "https://docs.litellm.ai/docs/search/exa_ai",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"search": true
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"empower": {
"display_name": "Empower (`empower`)",
"url": "https://docs.litellm.ai/docs/providers/empower",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"fal_ai": {
"display_name": "Fal AI (`fal_ai`)",
"url": "https://docs.litellm.ai/docs/providers/fal_ai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": true,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"featherless_ai": {
"display_name": "Featherless AI (`featherless_ai`)",
"url": "https://docs.litellm.ai/docs/providers/featherless_ai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"fireworks_ai": {
"display_name": "Fireworks AI (`fireworks_ai`)",
"url": "https://docs.litellm.ai/docs/providers/fireworks_ai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
Litellm 1 80 10 (#17945) * update providers * v0 * docs fix * docs fix * docs fix
2025-12-13 17:19:58 -08:00
"rerank": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
[Feat] /search API - add firecrawl search API support (#16257) * TestFirecrawlSearch * add SearchProviders * add to get_provider_search_config * add FirecrawlSearchConfig * add FirecrawlSearchRequest * add firecrawl API docs * add pricing firecrawl/search * add new search APIs
2025-11-04 17:52:12 -08:00
"firecrawl": {
"display_name": "Firecrawl (`firecrawl`)",
"url": "https://docs.litellm.ai/docs/search/firecrawl",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"search": true
}
},
[Feat] New Search API Provider - LinkUp Search (#18174) * add linkup search provider * add Linkup Search docs * add get_provider_search_config * get_provider_search_config * add linkup/search provider * fix mypy linting
2025-12-18 14:27:36 +05:30
"linkup": {
"display_name": "Linkup (`linkup`)",
"url": "https://docs.litellm.ai/docs/search/linkup",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"search": true
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"friendliai": {
"display_name": "FriendliAI (`friendliai`)",
"url": "https://docs.litellm.ai/docs/providers/friendliai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"galadriel": {
"display_name": "Galadriel (`galadriel`)",
"url": "https://docs.litellm.ai/docs/providers/galadriel",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"github_copilot": {
"display_name": "GitHub Copilot (`github_copilot`)",
"url": "https://docs.litellm.ai/docs/providers/github_copilot",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
Add ChatGPT subscription support and responses bridge (#19030) * Add ChatGPT subscription support and responses bridge * Fix typing import for responses bridge * Guard device code timestamp parsing * add /v1/messages endpoint to chatgpt model
2026-01-19 14:37:45 +01:00
"chatgpt": {
"display_name": "ChatGPT Subscription (`chatgpt`)",
"url": "https://docs.litellm.ai/docs/providers/chatgpt",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"a2a": false,
"interactions": false
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"github": {
"display_name": "GitHub Models (`github`)",
"url": "https://docs.litellm.ai/docs/providers/github",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"vertex_ai": {
"display_name": "Google - Vertex AI (`vertex_ai`)",
"url": "https://docs.litellm.ai/docs/providers/vertex",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": true,
"audio_transcriptions": false,
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
"audio_speech": true,
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"moderations": false,
"batches": false,
[Feat] /ocr - Add VertexAI OCR provider support + cost tracking (#16216) * add VertexAIOCRConfig * __all__ = ["VertexAIOCRConfig"] add * add get_provider_ocr_config * use GenericLiteLLMParams for litellm params * fix _async_prepare_ocr_request * fix _prepare_ocr_request * fix get_complete_url * fix validate_environment * add safe_get_vertex_ai_project * add VertexAIOCRConfig * fix get_complete_url * add TestVertexAIOCR * add mistral-ocr-2505 cost * add OCR to provider info * docs vertex ai ocr * fix _handle_rate_limits * Potential fix for code scanning alert no. 3632: Clear-text logging of sensitive information Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> --------- Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2025-11-03 15:56:49 -08:00
"rerank": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"ocr": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
"interactions": true,
"vector_stores_search": true,
"count_tokens": true,
"fine_tuning": true,
"rag_ingest": true,
"rag_query": true,
"generateContent": true
[Feat] New model/provider - Adds support for Google Cloud Chirp3 HD on /speech (#17391) * docs vertex tts * place vertex ai types in file * use VertexAITextToSpeechConfig * use vertex_voice_dict * refactor docs * docs vertex ai chirp * TestVertexAITextToSpeechConfig * new provider vertex ai chirp3 * test_litellm_speech_vertex_ai_chirp * add vertex_ai/chirp cost trackign
2025-12-02 15:36:23 -08:00
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"gemini": {
"display_name": "Google AI Studio - Gemini (`gemini`)",
"url": "https://docs.litellm.ai/docs/providers/gemini",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
docs init
2025-12-17 02:27:00 +04:00
"interactions": true,
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
"a2a": true,
"vector_stores_search": true,
"count_tokens": true,
"rag_ingest": true,
"realtime": true,
"generateContent": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"gradient_ai": {
"display_name": "GradientAI (`gradient_ai`)",
"url": "https://docs.litellm.ai/docs/providers/gradient_ai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"groq": {
"display_name": "Groq AI (`groq`)",
"url": "https://docs.litellm.ai/docs/providers/groq",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"heroku": {
"display_name": "Heroku (`heroku`)",
"url": "https://docs.litellm.ai/docs/providers/heroku",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"hosted_vllm": {
"display_name": "Hosted VLLM (`hosted_vllm`)",
"url": "https://docs.litellm.ai/docs/providers/vllm",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
add vllm batches
2025-12-14 12:32:20 -08:00
"embeddings": true,
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
add vllm batches
2025-12-14 12:32:20 -08:00
"batches": true,
"files": true,
"rerank": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"huggingface": {
"display_name": "Huggingface (`huggingface`)",
"url": "https://docs.litellm.ai/docs/providers/huggingface",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"hyperbolic": {
"display_name": "Hyperbolic (`hyperbolic`)",
"url": "https://docs.litellm.ai/docs/providers/hyperbolic",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"watsonx": {
"display_name": "IBM - Watsonx.ai (`watsonx`)",
"url": "https://docs.litellm.ai/docs/providers/watsonx",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": false,
[Feat] Add audio transcriptions for WatsonX (#17160) * feat: add IBMWatsonXAudioTranscriptionConfig * init IBMWatsonXAudioTranscriptionConfig * add inits * test_watsonx_transcription_url_and_headers * docs watsox audio * docs watsonx audi * docs
2025-11-26 14:15:49 -08:00
"audio_transcriptions": true,
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"infinity": {
"display_name": "Infinity (`infinity`)",
"url": "https://docs.litellm.ai/docs/providers/infinity",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false
}
},
"jina_ai": {
"display_name": "Jina AI (`jina_ai`)",
"url": "https://docs.litellm.ai/docs/providers/jina_ai",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false
}
},
"lambda_ai": {
"display_name": "Lambda AI (`lambda_ai`)",
"url": "https://docs.litellm.ai/docs/providers/lambda_ai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"lemonade": {
"display_name": "Lemonade (`lemonade`)",
"url": "https://docs.litellm.ai/docs/providers/lemonade",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"litellm_proxy": {
"display_name": "LiteLLM Proxy (`litellm_proxy`)",
"url": "https://docs.litellm.ai/docs/providers/litellm_proxy",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": true,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"llamafile": {
"display_name": "Llamafile (`llamafile`)",
"url": "https://docs.litellm.ai/docs/providers/llamafile",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"lm_studio": {
"display_name": "LM Studio (`lm_studio`)",
"url": "https://docs.litellm.ai/docs/providers/lm_studio",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"maritalk": {
"display_name": "Maritalk (`maritalk`)",
"url": "https://docs.litellm.ai/docs/providers/maritalk",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"meta_llama": {
"display_name": "Meta - Llama API (`meta_llama`)",
"url": "https://docs.litellm.ai/docs/providers/meta_llama",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"mistral": {
"display_name": "Mistral AI API (`mistral`)",
"url": "https://docs.litellm.ai/docs/providers/mistral",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Feat] /ocr - Add VertexAI OCR provider support + cost tracking (#16216) * add VertexAIOCRConfig * __all__ = ["VertexAIOCRConfig"] add * add get_provider_ocr_config * use GenericLiteLLMParams for litellm params * fix _async_prepare_ocr_request * fix _prepare_ocr_request * fix get_complete_url * fix validate_environment * add safe_get_vertex_ai_project * add VertexAIOCRConfig * fix get_complete_url * add TestVertexAIOCR * add mistral-ocr-2505 cost * add OCR to provider info * docs vertex ai ocr * fix _handle_rate_limits * Potential fix for code scanning alert no. 3632: Clear-text logging of sensitive information Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> --------- Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2025-11-03 15:56:49 -08:00
"rerank": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"ocr": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"moonshot": {
"display_name": "Moonshot (`moonshot`)",
"url": "https://docs.litellm.ai/docs/providers/moonshot",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
[Feat] New LLM Provider - Docker Model Runner (#16948) * add DOCKER_MODEL_RUNNER * add DockerModelRunnerChatConfig Transorm * add docker_model_runner * add docker_model_runner * docs docker model runner * add DockerModelRunnerChatConfig * add docker_model_runner to providers * test_completion_hits_correct_url_and_body * fix sidebar * TestDockerModelRunnerIntegration * test_completion_with_custom_engine_and_host * docs docker model runner * docs fix
2025-11-21 16:09:32 -08:00
"docker_model_runner": {
"display_name": "Docker Model Runner (`docker_model_runner`)",
"url": "https://docs.litellm.ai/docs/providers/docker_model_runner",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Feat] New LLM Provider - Docker Model Runner (#16948) * add DOCKER_MODEL_RUNNER * add DockerModelRunnerChatConfig Transorm * add docker_model_runner * add docker_model_runner * docs docker model runner * add DockerModelRunnerChatConfig * add docker_model_runner to providers * test_completion_hits_correct_url_and_body * fix sidebar * TestDockerModelRunnerIntegration * test_completion_with_custom_engine_and_host * docs docker model runner * docs fix
2025-11-21 16:09:32 -08:00
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"morph": {
"display_name": "Morph (`morph`)",
"url": "https://docs.litellm.ai/docs/providers/morph",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
Add 5 AI providers using `openai_like` (#18362) * Add 5 AI providers using `openai_like`: * Synthetic.new * Apertis / Stima.tech * NanoGPT * Poe * Chutes.ai * Update additional missing locations
2025-12-23 02:05:54 -08:00
"nanogpt": {
"display_name": "NanoGPT (`nanogpt`)",
"endpoints": {
"chat_completions": true,
"messages": false,
"responses": false,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"a2a": false
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"nebius": {
"display_name": "Nebius AI Studio (`nebius`)",
"url": "https://docs.litellm.ai/docs/providers/nebius",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"nlp_cloud": {
"display_name": "NLP Cloud (`nlp_cloud`)",
"url": "https://docs.litellm.ai/docs/providers/nlp_cloud",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"novita": {
"display_name": "Novita AI (`novita`)",
"url": "https://novita.ai/models/llm?utm_source=github_litellm&utm_medium=github_readme&utm_campaign=github_link",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"nscale": {
"display_name": "Nscale (`nscale`)",
"url": "https://docs.litellm.ai/docs/providers/nscale",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"nvidia_nim": {
"display_name": "Nvidia NIM (`nvidia_nim`)",
"url": "https://docs.litellm.ai/docs/providers/nvidia_nim",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"oci": {
"display_name": "OCI (`oci`)",
"url": "https://docs.litellm.ai/docs/providers/oci",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"ollama": {
"display_name": "Ollama (`ollama`)",
"url": "https://docs.litellm.ai/docs/providers/ollama",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"ollama_chat": {
"display_name": "Ollama Chat (`ollama_chat`)",
"url": "https://docs.litellm.ai/docs/providers/ollama",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"oobabooga": {
"display_name": "Oobabooga (`oobabooga`)",
"url": "https://docs.litellm.ai/docs/providers/openai_compatible",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": true,
"audio_speech": true,
"moderations": true,
"batches": true,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"openai": {
"display_name": "OpenAI (`openai`)",
"url": "https://docs.litellm.ai/docs/providers/openai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": true,
"audio_transcriptions": true,
"audio_speech": true,
"moderations": true,
"batches": true,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
"container": true,
[Feat] New API Endpoint - Responses API (v1/responses/compact) (#18697) * init transform_compact_response_api_request * init acompact_responses * init async_compact_response_api_handler in llm http handler * init transform_compact_response_api_request for openai * init acompact_responses * fix acompact_responses * add OAI Compact API * docs responses API Compact * code qa checks * test_openai_compact_responses_api * fix mypy linting
2026-01-06 16:24:04 +05:30
"compact": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
"interactions": true,
"vector_store_files": true,
"vector_stores_create": true,
"vector_stores_search": true,
"assistants": true,
"container_files": true,
"fine_tuning": true,
"image_variations": true,
"rag_ingest": true,
"rag_query": true,
"realtime": true,
"text_completion": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"openai_like": {
"display_name": "OpenAI-like (`openai_like`)",
"url": "https://docs.litellm.ai/docs/providers/openai_compatible",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
"rerank": false,
"assistants": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"openrouter": {
"display_name": "OpenRouter (`openrouter`)",
"url": "https://docs.litellm.ai/docs/providers/openrouter",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
OpenRouter embeddings API support (#18391) * support for OpenRouter embeddings * add bearer * add content header
2026-01-07 19:27:31 +00:00
"embeddings": true,
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"ovhcloud": {
"display_name": "OVHCloud AI Endpoints (`ovhcloud`)",
"url": "https://docs.litellm.ai/docs/providers/ovhcloud",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
Add support of audio transcription for OVHcloud (#17305)
2025-12-01 21:26:39 -05:00
"audio_transcriptions": true,
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
[Feat] /search API - add firecrawl search API support (#16257) * TestFirecrawlSearch * add SearchProviders * add to get_provider_search_config * add FirecrawlSearchConfig * add FirecrawlSearchRequest * add firecrawl API docs * add pricing firecrawl/search * add new search APIs
2025-11-04 17:52:12 -08:00
"parallel_ai": {
"display_name": "Parallel AI (`parallel_ai`)",
"url": "https://docs.litellm.ai/docs/search/parallel_ai",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"search": true
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"perplexity": {
"display_name": "Perplexity AI (`perplexity`)",
"url": "https://docs.litellm.ai/docs/providers/perplexity",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Feat] /search API - add firecrawl search API support (#16257) * TestFirecrawlSearch * add SearchProviders * add to get_provider_search_config * add FirecrawlSearchConfig * add FirecrawlSearchRequest * add firecrawl API docs * add pricing firecrawl/search * add new search APIs
2025-11-04 17:52:12 -08:00
"rerank": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"search": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"petals": {
"display_name": "Petals (`petals`)",
"url": "https://docs.litellm.ai/docs/providers/petals",
"endpoints": {
"chat_completions": true,
[Feature]: Add Provider publicai.co (#17230) * init PublicAIChatConfig * add publicai * init public ai * add publicai * add publicai/swiss-ai models etc
2025-11-27 13:08:03 -08:00
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Feature]: Add Provider publicai.co (#17230) * init PublicAIChatConfig * add publicai * init public ai * add publicai * add publicai/swiss-ai models etc
2025-11-27 13:08:03 -08:00
}
},
Add 5 AI providers using `openai_like` (#18362) * Add 5 AI providers using `openai_like`: * Synthetic.new * Apertis / Stima.tech * NanoGPT * Poe * Chutes.ai * Update additional missing locations
2025-12-23 02:05:54 -08:00
"poe": {
"display_name": "Poe (`poe`)",
"endpoints": {
"chat_completions": true,
"messages": false,
"responses": false,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"a2a": false
}
},
[Feature]: Add Provider publicai.co (#17230) * init PublicAIChatConfig * add publicai * init public ai * add publicai * add publicai/swiss-ai models etc
2025-11-27 13:08:03 -08:00
"publicai": {
"display_name": "PublicAI (`publicai`)",
"url": "https://docs.litellm.ai/docs/providers/publicai",
"endpoints": {
"chat_completions": true,
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"predibase": {
"display_name": "Predibase (`predibase`)",
"url": "https://docs.litellm.ai/docs/providers/predibase",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"recraft": {
"display_name": "Recraft (`recraft`)",
"url": "https://docs.litellm.ai/docs/providers/recraft",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": true,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false
}
},
"replicate": {
"display_name": "Replicate (`replicate`)",
"url": "https://docs.litellm.ai/docs/providers/replicate",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
[Feat] New Provider - Add RunwayML Provider for video generations (#16505) * add RUNWAYML * init folders * add RunwayMLVideoConfig * add RUNWAYML_DEFAULT_API_VERSION * add RunwayMLVideoConfig * fix getting status * add async_transform_video_content_response * add runwayml transform_video_content_response * fix config.yaml * add runwayml docs * add runwayml to videos * docs runwayml video gen * add new models to model cost map * TestRunwayMLVideoTransformation * fix linting errors
2025-11-11 18:48:23 -08:00
"runwayml": {
"display_name": "RunwayML (`runwayml`)",
"url": "https://docs.litellm.ai/docs/providers/runwayml/videos",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": false,
[Feat] Add RunwayML Img Gen API support (#16557) * TestRunwaymlImageGeneration * fix RUNWAYML * rename * fix rename * get_runwayml_image_generation_config * get_runwayml_image_generation_config * TestRunwaymlImageGeneration * add RUNWAYML_POLLING_TIMEOUT * fix rnwayml transform img gen * runwayml_image_cost_calculator * runwayml_image_cost_calculator * docs runwayml * fix runwayML polling * test_get_first_default_fallback
2025-11-12 18:20:14 -08:00
"image_generations": true,
[Feat] New Provider - Add RunwayML Provider for video generations (#16505) * add RUNWAYML * init folders * add RunwayMLVideoConfig * add RUNWAYML_DEFAULT_API_VERSION * add RunwayMLVideoConfig * fix getting status * add async_transform_video_content_response * add runwayml transform_video_content_response * fix config.yaml * add runwayml docs * add runwayml to videos * docs runwayml video gen * add new models to model cost map * TestRunwayMLVideoTransformation * fix linting errors
2025-11-11 18:48:23 -08:00
"audio_transcriptions": false,
[Feat] RunwayML - Add support for /audio/speech `eleven_multilingual_v2 ` endpoint (#16604) * init RunwayMLTextToSpeechConfig * add RunwayMLTextToSpeechConfig * add RunwayMLTextToSpeechConfig * test_runwayml_tts_async * runway ml speech * fix voices * fix test * docs runway lm * add runwayml here * fix RunwayMLTextToSpeechConfig * test_openai_voice_mapping_to_runwayml
2025-11-13 14:32:09 -08:00
"audio_speech": true,
[Feat] New Provider - Add RunwayML Provider for video generations (#16505) * add RUNWAYML * init folders * add RunwayMLVideoConfig * add RUNWAYML_DEFAULT_API_VERSION * add RunwayMLVideoConfig * fix getting status * add async_transform_video_content_response * add runwayml transform_video_content_response * fix config.yaml * add runwayml docs * add runwayml to videos * docs runwayml video gen * add new models to model cost map * TestRunwayMLVideoTransformation * fix linting errors
2025-11-11 18:48:23 -08:00
"moderations": false,
"batches": false,
"rerank": false,
"video_generations": true
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"sagemaker_chat": {
"display_name": "Sagemaker Chat (`sagemaker_chat`)",
"url": "https://docs.litellm.ai/docs/providers/aws_sagemaker",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
[Feat] add serxng search API provider (#16259) * TestFirecrawlSearch * add SearchProviders * add to get_provider_search_config * add FirecrawlSearchConfig * add FirecrawlSearchRequest * add firecrawl API docs * add pricing firecrawl/search * add new search APIs * add SearXNGSearchConfig * add searxng/search * add serxng params * TestSearXNGSearch * docs serxng * docs fix * docs fix * docs serxng
2025-11-04 17:56:07 -08:00
"searxng": {
"display_name": "SearXNG (`searxng`)",
"url": "https://docs.litellm.ai/docs/search/searxng",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"search": true
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"sambanova": {
"display_name": "Sambanova (`sambanova`)",
"url": "https://docs.litellm.ai/docs/providers/sambanova",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
docs - add sap gen ai provider on LiteLLM (#17667)
2025-12-08 12:43:42 -08:00
"sap": {
"display_name": "SAP Generative AI Hub (`sap`)",
"url": "https://docs.litellm.ai/docs/providers/sap",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
docs - add sap gen ai provider on LiteLLM (#17667)
2025-12-08 12:43:42 -08:00
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"snowflake": {
"display_name": "Snowflake (`snowflake`)",
"url": "https://docs.litellm.ai/docs/providers/snowflake",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
Add 5 AI providers using `openai_like` (#18362) * Add 5 AI providers using `openai_like`: * Synthetic.new * Apertis / Stima.tech * NanoGPT * Poe * Chutes.ai * Update additional missing locations
2025-12-23 02:05:54 -08:00
"synthetic": {
"display_name": "Synthetic (`synthetic`)",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"a2a": false
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"text-completion-codestral": {
"display_name": "Text Completion Codestral (`text-completion-codestral`)",
"url": "https://docs.litellm.ai/docs/providers/codestral",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"text-completion-openai": {
"display_name": "Text Completion OpenAI (`text-completion-openai`)",
"url": "https://docs.litellm.ai/docs/providers/text_completion_openai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": true,
"audio_speech": true,
"moderations": true,
"batches": true,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"together_ai": {
"display_name": "Together AI (`together_ai`)",
"url": "https://docs.litellm.ai/docs/providers/togetherai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"topaz": {
"display_name": "Topaz (`topaz`)",
"url": "https://docs.litellm.ai/docs/providers/topaz",
"endpoints": {
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
"image_variations": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
[Feat] /search API - add firecrawl search API support (#16257) * TestFirecrawlSearch * add SearchProviders * add to get_provider_search_config * add FirecrawlSearchConfig * add FirecrawlSearchRequest * add firecrawl API docs * add pricing firecrawl/search * add new search APIs
2025-11-04 17:52:12 -08:00
"tavily": {
"display_name": "Tavily (`tavily`)",
"url": "https://docs.litellm.ai/docs/search/tavily",
"endpoints": {
"search": true
}
},
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"triton": {
"display_name": "Triton (`triton`)",
"url": "https://docs.litellm.ai/docs/providers/triton-inference-server",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"v0": {
"display_name": "V0 (`v0`)",
"url": "https://docs.litellm.ai/docs/providers/v0",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"vercel_ai_gateway": {
"display_name": "Vercel AI Gateway (`vercel_ai_gateway`)",
"url": "https://docs.litellm.ai/docs/providers/vercel_ai_gateway",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"vllm": {
"display_name": "VLLM (`vllm`)",
"url": "https://docs.litellm.ai/docs/providers/vllm",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
add vllm batches
2025-12-14 12:32:20 -08:00
"embeddings": true,
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
add vllm batches
2025-12-14 12:32:20 -08:00
"batches": true,
"files": true,
"rerank": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"volcengine": {
"display_name": "Volcengine (`volcengine`)",
"url": "https://docs.litellm.ai/docs/providers/volcano",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"voyage": {
"display_name": "Voyage AI (`voyage`)",
"url": "https://docs.litellm.ai/docs/providers/voyage",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
Litellm 1 80 10 (#17945) * update providers * v0 * docs fix * docs fix * docs fix
2025-12-13 17:19:58 -08:00
"rerank": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"wandb": {
"display_name": "WandB Inference (`wandb`)",
"url": "https://docs.litellm.ai/docs/providers/wandb_inference",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"watsonx_text": {
"display_name": "Watsonx Text (`watsonx_text`)",
"url": "https://docs.litellm.ai/docs/providers/watsonx",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"xai": {
"display_name": "xAI (`xai`)",
"url": "https://docs.litellm.ai/docs/providers/xai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Docs] Agent Gateway (#17454) * init litellm A2a client * simpler a2a client interface * test a2a * move a2a invoking tests * test fix * ensure a2a send message is tracked n logs * rename tags * add streaming handlng * add a2a invocation * add a2a invocation i cost calc * test_a2a_logging_payload * update invoke_agent_a2a * test_invoke_agent_a2a_adds_litellm_data * add A2a agent * fix endpoints on A2a * UI allow testing a2a endpoints * add agent imgs * add a2a as an endpoint * add a2a * docs a2a invoke * docs a2a * docs A2a invoke
2025-12-03 18:57:41 -08:00
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
},
"xinference": {
"display_name": "Xinference (`xinference`)",
"url": "https://docs.litellm.ai/docs/providers/xinference",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": true,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false
}
1.80.8 RC docs (#17605) * stash docs * docs fix * doc fix * docs fix
2025-12-06 10:40:00 -08:00
},
"zai": {
"display_name": "Z.AI (Zhipu AI) (`zai`)",
"url": "https://docs.litellm.ai/docs/providers/zai",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
1.80.8 RC docs (#17605) * stash docs * docs fix * doc fix * docs fix
2025-12-06 10:40:00 -08:00
}
},
"ragflow": {
"display_name": "RAGFlow (`ragflow`)",
"url": "https://docs.litellm.ai/docs/providers/ragflow",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
"vector_stores_create": true,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
1.80.8 RC docs (#17605) * stash docs * docs fix * doc fix * docs fix
2025-12-06 10:40:00 -08:00
}
},
"cursor": {
"display_name": "Cursor BYOK (`cursor`)",
"url": "https://docs.litellm.ai/docs/providers/cursor",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
1.80.8 RC docs (#17605) * stash docs * docs fix * doc fix * docs fix
2025-12-06 10:40:00 -08:00
}
[Feat] New Provider - add langgraph (#17783) * init LANGGRAPH * init LangGraphConfig * init LangGraphConfig types * init langgraph * init getting api base and key * init transform langgraph * fix SSE issues * test_langgraph_acompletion_non_streaming * add LangGraph to docs * docs: Setting Up a Local LangGraph Server * fix langgraph SSE * fix import uuid
2025-12-10 12:30:35 -08:00
},
"langgraph": {
"display_name": "LangGraph (`langgraph`)",
"url": "https://docs.litellm.ai/docs/providers/langgraph",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Feat] New Provider - add langgraph (#17783) * init LANGGRAPH * init LangGraphConfig * init LangGraphConfig types * init langgraph * init getting api base and key * init transform langgraph * fix SSE issues * test_langgraph_acompletion_non_streaming * add LangGraph to docs * docs: Setting Up a Local LangGraph Server * fix langgraph SSE * fix import uuid
2025-12-10 12:30:35 -08:00
}
[Docs] Add docs on using pydantic ai agents with LiteLLM A2a gateway (#18026) * init A2AProviderConfigManager * move file * move file * add pydnatic ai folder * init providers * test_pydantic_ai_non_streaming * fix import * INIT pydantic * use_a2a_form_fields * test_vertex_agent_engine_streaming * add agent_engine * init transform for agent engine * init agent engine * VertexAgentEngineSSEStreamIterator * sample * ui add new fields * fix vertex_credentials * working SSE iterator * TestVertexAgentEngineTransformRequest * fix code QA check * stash docs * docs fix * fix logo * docs fix * doc pydantic ai * docs pydantic ai * new provider * docs fix
2025-12-15 19:43:12 -08:00
},
[Docs] Litellm add docs vertex ai engine (#18027) * new provider doc * add to sidebar * stash docs * docs fix * docs vertex agent engine
2025-12-15 20:11:40 -08:00
"vertex_ai/agent_engine": {
"display_name": "Vertex AI Agent Engine (`vertex_ai/agent_engine`)",
"url": "https://docs.litellm.ai/docs/providers/vertex_ai_agent_engine",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
[Docs] Litellm add docs vertex ai engine (#18027) * new provider doc * add to sidebar * stash docs * docs fix * docs vertex agent engine
2025-12-15 20:11:40 -08:00
}
},
[Docs] Add docs on using pydantic ai agents with LiteLLM A2a gateway (#18026) * init A2AProviderConfigManager * move file * move file * add pydnatic ai folder * init providers * test_pydantic_ai_non_streaming * fix import * INIT pydantic * use_a2a_form_fields * test_vertex_agent_engine_streaming * add agent_engine * init transform for agent engine * init agent engine * VertexAgentEngineSSEStreamIterator * sample * ui add new fields * fix vertex_credentials * working SSE iterator * TestVertexAgentEngineTransformRequest * fix code QA check * stash docs * docs fix * fix logo * docs fix * doc pydantic ai * docs pydantic ai * new provider * docs fix
2025-12-15 19:43:12 -08:00
"pydantic_ai_agents": {
"display_name": "Pydantic AI Agents (`pydantic_ai_agents`)",
"url": "https://docs.litellm.ai/docs/providers/pydantic_ai_agent",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"a2a": true
}
v 1.80.11
2025-12-20 23:48:10 +05:30
},
"stability": {
"display_name": "Stability AI (`stability`)",
"url": "https://docs.litellm.ai/docs/providers/stability",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": true,
"image_edits": true,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false
}
},
"venice": {
"display_name": "Venice.ai (`venice`)",
"url": "https://docs.litellm.ai/docs/providers/venice",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) (#18373) * add BaseInteractionsTest * add interactions_api_handler * init bridge * init LiteLLMResponsesInteractionsConfig * LiteLLMResponsesInteractionsHandler * mv test * fixes api spec * docs * fix transform+iterators * docs fix * fix iterator
2025-12-23 22:30:22 +05:30
"a2a": true,
"interactions": true
v 1.80.11
2025-12-20 23:48:10 +05:30
}
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
},
"gigachat": {
"display_name": "GigaChat (`gigachat`)",
"url": "https://docs.litellm.ai/docs/providers/gigachat",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": true
}
},
"google_pse": {
"display_name": "Google PSE (`google_pse`)",
"url": "https://docs.litellm.ai/docs/search/google_pse",
"endpoints": {
"search": true
}
},
"milvus": {
"display_name": "Milvus (`milvus`)",
"url": "https://docs.litellm.ai/docs/providers/milvus_vector_stores",
"endpoints": {
"vector_stores_search": true
}
},
"minimax": {
"display_name": "Minimax (`minimax`)",
"url": "https://docs.litellm.ai/docs/providers/minimax",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true
}
},
"pg_vector": {
"display_name": "PG Vector (`pg_vector`)",
"url": "https://docs.litellm.ai/docs/providers/pg_vector",
"endpoints": {
"vector_stores_search": true
}
},
"helicone": {
"display_name": "Helicone (`helicone`)",
"url": "https://docs.litellm.ai/docs/providers/helicone",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true
}
},
"llamagate": {
"display_name": "LlamaGate (`llamagate`)",
"url": "https://docs.litellm.ai/docs/providers/llamagate",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true
}
},
"xiaomi_mimo": {
"display_name": "Xiaomi Mimo (`xiaomi_mimo`)",
"url": "https://docs.litellm.ai/docs/providers/xiaomi_mimo",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true
}
[Feat] New provider - Manus API on /responses, GET /responses (#18804) * init ManusResponsesAPIConfig * init MANUS ApI * init MANUS create responses * init MANUS * test_extract_agent_profile * transform_get_response_api_request * test fix * fixes non stream * fix streaming * add MANUSConfig * test_multiturn_responses_api * code QA check * add manus * Potential fix for code scanning alert no. 3961: Clear-text logging of sensitive information Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> --------- Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2026-01-08 18:37:42 +05:30
},
"manus": {
"display_name": "Manus (`manus`)",
"url": "https://docs.litellm.ai/docs/providers/manus",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
[Feat] Manus FILES API - Add File upload, get, delete, list (#18904) * add MANUS get response * init TwoStepFileUploadRequest * init TwoStepFileUploadConfig * add async_create_file to handle 2 step uploads * init ManusFilesConfig * add add get_provider_files_config MANUS * fix validate_environment * test_manus_files_api_e2e_all_methods * aws fix base * init files API MANUS * test_manus_responses_api_with_file_upload * mypy lint fixes * fix BedrockFilesConfig * manus docs * docs manus * mypy lint * add add fix resposne api utils MANUS
2026-01-11 01:27:54 +04:00
"files": true,
[Feat] New provider - Manus API on /responses, GET /responses (#18804) * init ManusResponsesAPIConfig * init MANUS ApI * init MANUS create responses * init MANUS * test_extract_agent_profile * transform_get_response_api_request * test fix * fixes non stream * fix streaming * add MANUSConfig * test_multiturn_responses_api * code QA check * add manus * Potential fix for code scanning alert no. 3961: Clear-text logging of sensitive information Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> --------- Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2026-01-08 18:37:42 +05:30
"rerank": false,
"a2a": true,
"interactions": true
}
Litellm improve endpoint discovery (#18762) * docs: document all endpoints in .json and add consistency checks against docs + providers.json * docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
}
},
"endpoints": {
"a2a": {
"docs_label": "a2a",
"display_name": "A2A (Agent-to-Agent) protocol for agent communication",
"leftnav_label": "/a2a",
"provider_json_field": "a2a",
"url": "https://docs.litellm.ai/docs/a2a",
"bridges_to_chat_completion": true
},
"messages": {
"docs_label": "anthropic_unified",
"display_name": "Anthropic /v1/messages API",
"leftnav_label": "/messages",
"provider_json_field": "messages",
"url": "https://docs.litellm.ai/docs/anthropic_unified",
"bridges_to_chat_completion": true
},
"anthropic_count_tokens": {
"docs_label": "anthropic_count_tokens",
"display_name": "Anthropic /v1/messages/count_tokens API",
"leftnav_label": "/count_tokens",
"provider_json_field": "count_tokens",
"url": "https://docs.litellm.ai/docs/anthropic_count_tokens"
},
"apply_guardrail": {
"docs_label": "apply_guardrail",
"display_name": "Unified Apply Guardrail API",
"leftnav_label": "/guardrails/apply_guardrail",
"provider_json_field": "apply_guardrail",
"url": "https://docs.litellm.ai/docs/apply_guardrail"
},
"assistants": {
"docs_label": "assistants",
"display_name": "OpenAI Assistants API",
"leftnav_label": "/assistants",
"provider_json_field": "assistants",
"url": "https://docs.litellm.ai/docs/assistants"
},
"audio_transcription": {
"docs_label": "audio_transcription",
"display_name": "Audio Transcription API",
"leftnav_label": "/audio/transcriptions",
"provider_json_field": "audio_transcriptions",
"url": "https://docs.litellm.ai/docs/audio_transcription"
},
"batches": {
"docs_label": "batches",
"display_name": "Batches API",
"leftnav_label": "/batches",
"provider_json_field": "batches",
"url": "https://docs.litellm.ai/docs/batches"
},
"bedrock_invoke": {
"docs_label": "bedrock_invoke",
"display_name": "Bedrock Invoke API",
"leftnav_label": "/invoke",
"provider_json_field": "bedrock_invoke",
"url": "https://docs.litellm.ai/docs/bedrock_invoke"
},
"bedrock_converse": {
"docs_label": "bedrock_converse",
"display_name": "Bedrock Converse API",
"leftnav_label": "/converse",
"provider_json_field": "bedrock_converse",
"url": "https://docs.litellm.ai/docs/bedrock_converse"
},
"chat_completions": {
"docs_label": "chat_completions",
"display_name": "Chat Completions API",
"leftnav_label": "/chat/completions",
"provider_json_field": "chat_completions",
"url": "https://docs.litellm.ai/docs/chat_completions"
},
"container_files": {
"docs_label": "container_files",
"display_name": "OpenAI Container Files API",
"leftnav_label": "/create/container/files",
"provider_json_field": "container_files",
"url": "https://docs.litellm.ai/docs/container_files"
},
"container": {
"docs_label": "containers",
"display_name": "OpenAI Containers API",
"leftnav_label": "/container",
"provider_json_field": "container",
"url": "https://docs.litellm.ai/docs/containers"
},
"embeddings": {
"docs_label": "embedding/supported_embedding",
"display_name": "Embedding API (OpenAI Format)",
"leftnav_label": "/embeddings",
"provider_json_field": "embeddings",
"url": "https://docs.litellm.ai/docs/embedding/supported_embedding"
},
"files": {
"docs_label": "files",
"display_name": "OpenAI Files API",
"leftnav_label": "/files",
"provider_json_field": "files",
"url": "https://docs.litellm.ai/docs/proxy/litellm_managed_files"
},
"fine_tuning": {
"docs_label": "fine_tuning",
"display_name": "OpenAI Fine-Tuning API",
"leftnav_label": "/fine_tuning",
"provider_json_field": "fine_tuning",
"url": "https://docs.litellm.ai/docs/proxy/managed_finetuning"
},
"generateContent": {
"docs_label": "generateContent",
"display_name": "Google's GenerateContent API",
"leftnav_label": "/generateContent",
"provider_json_field": "generateContent",
"url": "https://docs.litellm.ai/docs/generateContent",
"bridges_to_chat_completion": true
},
"image_edits": {
"docs_label": "image_edits",
"display_name": "OpenAI Images Edits API",
"leftnav_label": "/images/edits",
"provider_json_field": "image_edits",
"url": "https://docs.litellm.ai/docs/image_edits"
},
"image_generations": {
"docs_label": "image_generation",
"display_name": "OpenAI Images Generations API",
"leftnav_label": "/images/generations",
"provider_json_field": "image_generations",
"url": "https://docs.litellm.ai/docs/image_generation"
},
"image_variations": {
"docs_label": "image_variations",
"display_name": "OpenAI Images Variations API",
"leftnav_label": "/images/variations",
"provider_json_field": "image_variations",
"url": "https://docs.litellm.ai/docs/image_variations"
},
"interactions": {
"docs_label": "interactions",
"display_name": "Google Interactions API",
"leftnav_label": "/interactions",
"provider_json_field": "interactions",
"url": "https://docs.litellm.ai/docs/interactions",
"bridges_to_chat_completion": true
},
"mcp": {
"docs_label": "mcp",
"display_name": "Model Context Protocol (MCP)",
"leftnav_label": "/mcp",
"provider_json_field": "mcp",
"url": "https://docs.litellm.ai/docs/mcp"
},
"moderation": {
"docs_label": "moderation",
"display_name": "OpenAI Moderation API",
"leftnav_label": "/moderations",
"provider_json_field": "moderations",
"url": "https://docs.litellm.ai/docs/moderation"
},
"ocr": {
"docs_label": "ocr",
"display_name": "OCR API (Mistral Format)",
"leftnav_label": "/ocr",
"provider_json_field": "ocr",
"url": "https://docs.litellm.ai/docs/ocr"
},
"rag_ingest": {
"docs_label": "rag_ingest",
"display_name": "RAG Ingest API",
"leftnav_label": "/rag/ingest",
"provider_json_field": "rag_ingest",
"url": "https://docs.litellm.ai/docs/rag_ingest"
},
"rag_query": {
"docs_label": "rag_query",
"display_name": "RAG Query API",
"leftnav_label": "/rag/query",
"provider_json_field": "rag_query",
"url": "https://docs.litellm.ai/docs/rag_query"
},
"realtime": {
"docs_label": "realtime",
"display_name": "OpenAI Realtime API",
"leftnav_label": "/realtime",
"provider_json_field": "realtime",
"url": "https://docs.litellm.ai/docs/realtime"
},
"rerank": {
"docs_label": "rerank",
"display_name": "Rerank API (Cohere Format)",
"leftnav_label": "/rerank",
"provider_json_field": "rerank",
"url": "https://docs.litellm.ai/docs/rerank"
},
"responses": {
"docs_label": "response_api",
"display_name": "Responses API (OpenAI Format)",
"leftnav_label": "/responses",
"provider_json_field": "responses",
"url": "https://docs.litellm.ai/docs/response_api",
"bridges_to_chat_completion": true
},
"response_api_compact": {
"docs_label": "response_api_compact",
"display_name": "Responses API (OpenAI Format)",
"leftnav_label": "/responses",
"provider_json_field": "compact",
"url": "https://docs.litellm.ai/docs/response_api"
},
"search": {
"docs_label": "search",
"display_name": "Search API",
"leftnav_label": "/search",
"provider_json_field": "search",
"url": "https://docs.litellm.ai/docs/search"
},
"skills": {
"docs_label": "skills",
"display_name": "Anthropic Skills API",
"leftnav_label": "/skills",
"provider_json_field": "skills",
"url": "https://docs.litellm.ai/docs/skills"
},
"text_completion": {
"docs_label": "text_completion",
"display_name": "Completions API (OpenAI Format)",
"leftnav_label": "/completions",
"provider_json_field": "text_completion",
"url": "https://docs.litellm.ai/docs/text_completion",
"bridges_to_chat_completion": true
},
"text_to_speech": {
"docs_label": "text_to_speech",
"display_name": "Text-to-Speech API (OpenAI Format)",
"leftnav_label": "/audio/speech",
"provider_json_field": "audio_speech",
"url": "https://docs.litellm.ai/docs/text_to_speech"
},
"vector_store_files": {
"docs_label": "vector_store_files",
"display_name": "OpenAI Vector Store Files API",
"leftnav_label": "/vector_stores/files",
"provider_json_field": "vector_store_files",
"url": "https://docs.litellm.ai/docs/vector_store_files"
},
"vector_stores_create": {
"docs_label": "vector_stores_create",
"display_name": "OpenAI Vector Stores Create API",
"leftnav_label": "/vector_stores/create",
"provider_json_field": "vector_stores_create",
"url": "https://docs.litellm.ai/docs/vector_stores/create"
},
"vector_stores_search": {
"docs_label": "vector_stores_search",
"display_name": "OpenAI Vector Stores Search API",
"leftnav_label": "/vector_stores/search",
"provider_json_field": "vector_stores_search",
"url": "https://docs.litellm.ai/docs/vector_stores/search"
},
"videos": {
"docs_label": "videos",
"display_name": "OpenAI Video Generation API",
"leftnav_label": "/videos",
"provider_json_field": "video_generations",
"url": "https://docs.litellm.ai/docs/videos"
[Docs] readme fixes add supported providers (#16109) * add provider test * docs readme.md * docs providers * order providers * test_providers_alphabetically_ordered * docs endpoint * fix config * add ENDPOINT_COLUMNS * add provider endpoints * docs fix
2025-10-30 17:23:20 -07:00
}
}
Add 5 AI providers using `openai_like` (#18362) * Add 5 AI providers using `openai_like`: * Synthetic.new * Apertis / Stima.tech * NanoGPT * Poe * Chutes.ai * Update additional missing locations
2025-12-23 02:05:54 -08:00
}
Reference in New Issue Copy Permalink