scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-11 03:38:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 84
litellm/litellm/llms
History
Exact
Sameer Kankute a788b21092
Merge pull request #23243 from BerriAI/litellm_bedrock-completion-tokens-details 
fix(bedrock): populate completion_tokens_details in Responses API
2026-03-10 18:19:28 +05:30
..
a2a Agent Guardrails - on streaming output (#21206) 2026-02-14 11:36:52 -08:00
ai21/chat (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
aiml fix ai/ml api 2025-11-26 18:55:55 -08:00
aiohttp_openai/chat VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
amazon_nova amazon nova api fix 2025-12-06 16:09:27 -08:00
anthropic fix(anthropic/skills): remove ?beta=true query param from Skills API URLs (#23069) 2026-03-07 16:46:26 -08:00
aws_polly [Feat] New provider TTS - Add AWS polly API for TTS (#18326) 2025-12-22 18:19:34 +05:30
azure fix(openai): preserve reasoning_effort summary + fix xhigh/none guards for dict inputs 2026-03-09 18:44:05 +05:30
azure_ai feat(azure_ai): add router flat cost when response contains actual model 2026-03-06 18:18:06 +05:30
base_llm Add supports_native_websocket to handle providers who don't handle websocket 2026-03-04 18:26:16 +05:30
baseten lint 2025-08-19 13:36:41 -07:00
bedrock fix(bedrock): populate completion_tokens_details in converse _transform_usage 2026-03-10 13:17:28 +05:30
bedrock_mantle/chat feat(provider): add Amazon Bedrock Mantle as a first-class provider 2026-03-05 00:03:40 -05:00
brave/search add search provider for brave search api (#19433) 2026-01-20 19:23:29 -08:00
bytez ruff check ./litellm --fix 2025-07-12 11:04:02 -07:00
cerebras fix: add reasoning param support for GPT OSS cerebras 2026-02-02 17:20:04 +05:30
chatgpt Add supports_native_websocket to handle providers who don't handle websocket 2026-03-04 18:26:16 +05:30
clarifai/chat UI - add arize on ui, LLMs - clarifai refactor to openai compatible route, added azure ai/grok-4 model family 2025-10-16 20:39:15 -07:00
cloudflare/chat VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
codestral/completion fix(types): remove StreamingChoices from ModelResponse, use ModelResponseStream 2026-02-20 17:47:42 -03:00
cohere Feature/guardrail model argument (#19619) 2026-01-23 20:48:42 -08:00
cometapi feat(cometapi): Add CometAPI provider support (embeddings, image generation, docs) 2025-10-16 13:08:14 +08:00
compactifai Fix CompactifAI provider tests and implementation 2025-09-15 22:03:42 +02:00
custom_httpx Revert "fix: strip empty text content blocks in /v1/messages endpoint (#23097)" 2026-03-10 09:53:19 +05:30
dashscope fix: remove list-to-str transformation from dashscope 2026-02-19 07:30:13 +00:00
databricks Add supports_native_websocket to handle providers who don't handle websocket 2026-03-04 18:26:16 +05:30
dataforseo/search [Feat] UI - Search Tools, allow adding search tools on UI + testing search (#15871) 2025-10-23 17:59:29 -07:00
datarobot/chat Updated URL handling for DataRobot provider base 2025-08-21 19:42:46 -06:00
deepgram fix mypy lint 2025-11-03 18:02:19 -08:00
deepinfra fix mypy error 2026-01-08 15:38:28 +05:30
deepseek feat(deepseek): add native support for thinking and reasoning_effort params (#17712) 2025-12-11 15:28:43 -08:00
deprecated_providers fix(mypy): resolve type checking errors in 5 files (#20627) 2026-02-06 18:34:55 -08:00
docker_model_runner/chat [Feat] New LLM Provider - Docker Model Runner (#16948) 2025-11-21 16:09:32 -08:00
duckduckgo/search Add duckcukgo in model map 2026-02-18 16:13:20 +05:30
elevenlabs Integrate eleven labs text-to-speech (#16573) 2025-11-24 18:49:30 -08:00
empower/chat LiteLLM Common Base LLM Config (pt.3): Move all OAI compatible providers to base llm config (#7148) 2024-12-10 17:12:42 -08:00
exa_ai/search [Feat] UI - Search Tools, allow adding search tools on UI + testing search (#15871) 2025-10-23 17:59:29 -07:00
fal_ai fix QA check 2025-11-15 13:02:48 -08:00
featherless_ai/chat fix(featherless_ai): use correct FEATHERLESS_AI_API_KEY env var name 2026-03-01 17:11:58 +01:00
firecrawl [Feat] /search API - add firecrawl search API support (#16257) 2025-11-04 17:52:12 -08:00
fireworks_ai fix(fireworks): strip duplicate /v1 from models endpoint URL (#23113) 2026-03-09 19:49:58 -07:00
friendliai/chat (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
galadriel/chat (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
gemini Fix mypy override errors in count_tokens signatures 2026-03-03 18:15:27 -03:00
gigachat bugfix: Remove user messages merging 2026-02-03 12:58:28 +00:00
github/chat (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
github_copilot Add supports_native_websocket to handle providers who don't handle websocket 2026-03-04 18:26:16 +05:30
google_pse/search [Feat] UI - Search Tools, allow adding search tools on UI + testing search (#15871) 2025-10-23 17:59:29 -07:00
gradient_ai/chat Add digitalocean provider (#12169) 2025-08-09 16:26:33 -07:00
groq Add grok reasoning content 2026-01-27 16:34:57 +05:30
heroku/chat fixes linter error 2025-07-28 09:44:02 -06:00
hosted_vllm Add supports_native_websocket to handle providers who don't handle websocket 2026-03-04 18:26:16 +05:30
huggingface Use vertex creds passed via arguments (#16266) 2025-11-06 19:35:22 -08:00
hyperbolic Revert "Litellm dev 07 21 2025 p1 (#12848)" 2025-07-22 18:28:36 -07:00
infinity Use vertex creds passed via arguments (#16266) 2025-11-06 19:35:22 -08:00
jina_ai Use vertex creds passed via arguments (#16266) 2025-11-06 19:35:22 -08:00
lambda_ai Revert "Litellm dev 07 21 2025 p1 (#12848)" 2025-07-22 18:28:36 -07:00
langgraph fix(lint): update return/yield types to ModelResponseStream 2026-02-22 09:17:36 -03:00
lemonade Removing unecessary import 2025-09-30 12:12:24 -06:00
linkup [Feat] New Search API Provider - LinkUp Search (#18174) 2025-12-18 14:27:36 +05:30
litellm_proxy Add supports_native_websocket to handle providers who don't handle websocket 2026-03-04 18:26:16 +05:30
llamafile/chat Add llamafile as a provider (#10203) (#10482) 2025-05-01 18:36:55 -07:00
lm_studio fix(lm_studio): resolve illegal Bearer header value issue 2025-09-12 22:41:30 +02:00
manus Add supports_native_websocket to handle providers who don't handle websocket 2026-03-04 18:26:16 +05:30
meta_llama/chat [Feat] Enable Tool Calling for meta_llama (#11895) 2025-06-19 13:44:22 -07:00
milvus/vector_stores docs: document milvus endpoints 2025-11-01 12:17:02 -07:00
minimax Add Prompt caching and reasoning support for MiniMax, GLM, Xiaomi 2026-01-28 17:25:26 +05:30
mistral Add OCR guardrail_translation handler and support (#22145) 2026-02-28 17:39:36 -08:00
moonshot/chat fix(moonshot): preserve image_url blocks in multimodal messages 2026-02-19 16:44:38 -03:00
morph fix morph api tests 2025-07-22 18:44:44 -07:00
nebius Integration with Nebius AI Studio added (#11143) 2025-05-27 11:05:22 -07:00
nlp_cloud VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
novita/chat Add new model provider Novita AI (#7582) (#9527) 2025-05-12 21:49:30 -07:00
nscale/chat Add nscale support for streaming (#10698) 2025-05-09 11:39:23 -07:00
nvidia_nim Fix nvdia and geminin tests 2025-12-10 22:05:11 +05:30
oci Fixes #20957 2026-02-11 11:20:18 +00:00
ollama fix(ollama): thread api_base to get_model_info + graceful fallback (#21970) 2026-02-23 21:00:37 -08:00
oobabooga VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
openai fix(openai): preserve reasoning_effort summary + fix xhigh/none guards for dict inputs 2026-03-09 18:44:05 +05:30
openai_like feat(charity_engine): add Charity Engine provider (#23223) 2026-03-09 20:46:43 -07:00
openrouter fix(mypy): resolve type errors across 9 files 2026-03-05 06:58:20 -03:00
ovhcloud [Refactor#2] litellm/init – Lazy-load utils to reduce memory + import time (#17171) 2025-12-03 11:40:16 -08:00
parallel_ai/search [Feat] UI - Search Tools, allow adding search tools on UI + testing search (#15871) 2025-10-23 17:59:29 -07:00
pass_through Feature/guardrail model argument (#19619) 2026-01-23 20:48:42 -08:00
perplexity Add supports_native_websocket to handle providers who don't handle websocket 2026-03-04 18:26:16 +05:30
petals VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
pg_vector/vector_stores [Feat] UI Vector Stores - Allow adding Vertex RAG Engine, OpenAI, Azure (#12752) 2025-07-18 18:25:26 -07:00
predibase VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
ragflow Fix unused imports 2025-12-03 15:32:42 +05:30
recraft Fix: stability image optional para 2026-01-19 09:05:52 +05:30
replicate Fix Output None for replicate handler 2026-01-19 17:22:06 +05:30
runwayml fix(ollama): thread api_base to get_model_info + graceful fallback (#21970) 2026-02-23 21:00:37 -08:00
s3_vectors [Feat] RAG API - Add s3_vectors as provider on /vector_store/search API + UI for creating + PDF support for /rag/ingest (#19895) 2026-01-27 16:30:59 -08:00
sagemaker fix(sagemaker): Add role assumption support for embedding endpoint (#20435) 2026-03-09 20:58:14 -07:00
sambanova Fix : acompletion throws error with SambaNova models (#17217) 2025-11-27 21:59:24 -08:00
sap fix(sap provider layer): enable response-format for anthropic models and improve compatibility for GPT models via LangChain (#22804) 2026-03-04 16:03:59 -08:00
searchapi CircleCI test stability (#23055) 2026-03-07 15:19:39 -08:00
searxng [Feat] add serxng search API provider (#16259) 2025-11-04 17:56:07 -08:00
serper/search feat(search): add Serper (serper.dev) as search provider (#23112) 2026-03-09 08:40:37 -07:00
snowflake Snowflake provider support: added embeddings, PAT, account_id (#15727) 2025-11-17 20:27:46 -08:00
stability Fix: stability image optional para 2026-01-19 09:05:52 +05:30
tavily/search [Feat] UI - Search Tools, allow adding search tools on UI + testing search (#15871) 2025-10-23 17:59:29 -07:00
together_ai [Refactor#2] litellm/init – Lazy-load utils to reduce memory + import time (#17171) 2025-12-03 11:40:16 -08:00
topaz Add /vllm/* and /mistral/* passthrough endpoints (adds support for Mistral OCR via passthrough) 2025-04-14 22:06:33 -07:00
triton fix(triton/completion/transformation.py): remove bad_words / stop wor… (#10163) 2025-04-19 11:23:37 -07:00
v0 feat: add v0 provider support (#12751) 2025-07-18 18:26:44 -07:00
vercel_ai_gateway feat(vercel_ai_gateway): add embeddings support 2026-01-23 15:11:37 -03:00
vertex_ai fix(vertex_ai): strip LiteLLM-internal keys from extra_body before merging to Gemini request 2026-03-09 10:21:29 +05:30
vllm fix vllm passthrough 2025-09-22 10:09:02 -03:00
volcengine Add supports_native_websocket to handle providers who don't handle websocket 2026-03-04 18:26:16 +05:30
voyage [Fix] CI/CD – Clean Up Performance PR Changes & others (#17838) 2025-12-11 12:50:03 -08:00
wandb (feat): Add W&B Inference to LiteLLM 2025-09-11 00:07:30 +05:30
watsonx feat: Add IBM watsonx.ai rerank support (#21303) 2026-02-16 20:12:16 -08:00
xai Add supports_native_websocket to handle providers who don't handle websocket 2026-03-04 18:26:16 +05:30
xinference/image_generation [Feat] Add XInference Image Generation API Provider (#12439) 2025-07-08 21:17:38 -07:00
zai Add Prompt caching and reasoning support for MiniMax, GLM, Xiaomi 2026-01-28 17:25:26 +05:30
__init__.py fix: move code from litellm/llms to the mcp_server dir 2026-01-05 12:05:16 +09:00
base.py Gemini - web search cost tracking + Update max output tokens for nova models 2025-06-05 23:25:18 -07:00
custom_llm.py Fix mypy issues 2026-01-16 14:47:56 +05:30
maritalk.py build(pyproject.toml): add new dev dependencies - for type checking (#9631) 2025-03-29 11:02:13 -07:00
README.md LiteLLM Minor Fixes and Improvements (09/13/2024) (#5689) 2024-09-14 10:02:55 -07:00

README.md

File Structure

August 27th, 2024

To make it easy to see how calls are transformed for each model/provider:

we are working on moving all supported litellm providers to a folder structure, where folder name is the supported litellm provider name.

Each folder will contain a *_transformation.py file, which has all the request/response transformation logic, making it easy to see how calls are modified.

E.g. cohere/, bedrock/.