scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-29 06:33:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 200
litellm/litellm/llms
History
devin-ai-integration[bot] fdab308646
fix(vertex_ai): keep Gemini cache creation token count out of request kwargs (#46152)
2026-10-12 21:19:12 -07:00
..
a2a refactor(sdk): import UserAPIKeyAuth from litellm.types.proxy.auth (#45806) 2026-10-10 21:27:48 +00:00
ai21/chat feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
aiml refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
aiohttp_openai/chat refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
amazon_nova feat(tokenizer): preserve Python defaults with opt-in Rust dispatch (#42174) 2026-09-22 04:41:11 +00:00
anthropic fix(cost_calculator): apply the anthropic fast multiplier to cache cost breakdown (#46112) 2026-10-12 17:38:08 -07:00
apiserpent feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
aws_polly refactor(sdk): separate core AWS and tokenizer dependencies (#44447) 2026-10-08 19:07:57 -07:00
azure fix: support OpenAI SDK 3 while retaining SDK 2 compatibility (#44927) 2026-10-09 19:45:50 -07:00
azure_ai feat(azure_ai): support Microsoft-Decision-1 on the decisions API (#45673) 2026-10-09 16:40:43 -07:00
base_llm feat(decisions): support Clef-omni audio and video (#45811) 2026-10-12 20:29:49 +00:00
baseten feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
bedrock refactor(bedrock): rename is_claude_4_5_on_bedrock to supports_bedrock_prompt_cache_ttl (#46058) 2026-10-12 18:34:33 +00:00
bedrock_mantle fix(bedrock_mantle): send max_completion_tokens for gpt-5.6 and gpt-6 chat completions (#43982) 2026-10-11 18:28:48 +00:00
black_forest_labs refactor(types): replace Any with proven types in 3 files (#45565) 2026-10-09 03:24:16 -07:00
brave/search feat(tokenizer): preserve Python defaults with opt-in Rust dispatch (#42174) 2026-09-22 04:41:11 +00:00
bytez refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
cerebras fix(cerebras): add max_retries and extra_headers to get_supported_openai_params (#36601) 2026-08-25 14:10:56 -07:00
chatgpt refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
clarifai/chat refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
claude_code refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
cloudflare refactor(decisions): dispatch /v1/decisions through provider configs and the shared HTTP handler (#45130) 2026-10-07 19:45:45 -07:00
codestral/completion refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
codex refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
cohere refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
cometapi refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
compactifai feat(tokenizer): preserve Python defaults with opt-in Rust dispatch (#42174) 2026-09-22 04:41:11 +00:00
custom_httpx refactor(sdk): import UserAPIKeyAuth from litellm.types.proxy.auth (#45806) 2026-10-10 21:27:48 +00:00
dashscope refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
databricks fix(databricks): accept service_tier on requests and carry the served tier on responses (#46111) 2026-10-12 18:22:10 -07:00
dataforseo/search refactor(typing): replace Any with proven types in 42 more backend files 2026-09-02 15:35:01 +00:00
datarobot/chat refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
deepagents refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
deepgram refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
deepinfra refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
deepseek refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
deprecated_providers feat(tokenizer): preserve Python defaults with opt-in Rust dispatch (#42174) 2026-09-22 04:41:11 +00:00
docker_model_runner/chat refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
duckduckgo/search feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
e2b refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
edenai perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
elevenlabs refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
empower/chat
exa_ai/search fix(exa): fall back to highlights/summary when text is missing (#42213) 2026-10-02 14:15:15 -07:00
fal_ai refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
fastcrw feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
featherless_ai/chat refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
firecrawl feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
fireworks_ai feat(fireworks_ai): add Decisions support for accounts/fireworks/routers/rune on /v1/systemone and /v1/decisions (#46057) 2026-10-12 11:18:59 -07:00
friendliai/chat
galadriel/chat
gdc refactor(types): replace Any with real types across 29 more backend files 2026-09-08 10:14:07 +00:00
gemini refactor(types): replace Any with proven types in 12 files (#45943) 2026-10-11 06:34:46 -07:00
gigachat refactor: move stream_chunk_builder into streaming_chunk_builder_utils (#45766) 2026-10-10 19:06:41 +00:00
github/chat
github_copilot feat(github_copilot): per-user GitHub OAuth connections for Copilot credentials (#45241) 2026-10-09 15:19:07 -07:00
google_pse/search feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
gradient_ai/chat refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
groq refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
heroku/chat refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
hosted_vllm feat(decisions): add hosted_vllm provider (#45501) 2026-10-09 10:41:51 -07:00
huggingface refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
hyperbolic refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
inception refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
infinity Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_decrease_anys_opus5 2026-08-29 06:03:33 -07:00
jina_ai refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
lambda_ai refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
langflow refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
langgraph refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
laya perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
lemonade refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
linkup feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
litellm_proxy refactor(sdk): import UserAPIKeyAuth from litellm.types.proxy.auth (#45806) 2026-10-10 21:27:48 +00:00
llamafile/chat refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
lm_studio refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
manus refactor(types): replace Any with proven types in 16 files (#45029) 2026-10-07 04:31:51 -07:00
meta/realtime chore(lint): remove the LIT002 mutable-construction rule (#43971) 2026-10-01 12:24:02 -07:00
meta_llama/chat feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
microsoft_365_copilot feat(microsoft_365_copilot): add Microsoft 365 Copilot chat provider with OAuth token exchange (#45158) 2026-10-09 15:19:07 -07:00
milvus/vector_stores refactor(s3_vectors): embed search queries through the shared vector store executor 2026-09-02 19:26:31 -07:00
minimax refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
mistral refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
modelscope refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
mongodb perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
moonshot/chat refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
morph refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
nadir/chat chore(lint): remove the LIT002 mutable-construction rule (#43971) 2026-10-01 12:24:02 -07:00
nebius feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
nimble perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
nlp_cloud refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
novita/chat fix(openai-compat): send provider attribution headers on the default SDK path (+ Perplexity) (#44291) 2026-10-07 13:21:27 -07:00
nscale/chat refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
nvidia_nim refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
nvidia_riva refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
oci refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
ollama fix(ollama): one stream id, 400 on non-text tool content, separated tool results, no empty message item (#45177) 2026-10-07 19:08:26 -07:00
oobabooga refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
openai feat(decisions): support Clef-omni audio and video (#45811) 2026-10-12 20:29:49 +00:00
openai_like feat(providers): add CoralBricks as a native provider (#44700) 2026-10-12 21:56:59 +00:00
opencode refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
openrouter refactor(types): replace Any with proven types in 12 files (#45943) 2026-10-11 06:34:46 -07:00
opensandbox refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
ovhcloud refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
parallel_ai/search perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
pass_through feat(decisions): bill decisions and systemone from _decisions cost map fields (#45904) 2026-10-12 14:31:12 -07:00
perplexity refactor(decisions): dispatch /v1/decisions through provider configs and the shared HTTP handler (#45130) 2026-10-07 19:45:45 -07:00
petals refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
pg_vector/vector_stores refactor(s3_vectors): embed search queries through the shared vector store executor 2026-09-02 19:26:31 -07:00
predibase refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
ragflow refactor(types): replace Any with proven types in 12 files (#45943) 2026-10-11 06:34:46 -07:00
recraft refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
reducto refactor(ocr): remove the Python OCR execution path and require the Rust route (#43081) 2026-09-24 18:18:50 -07:00
replicate refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
runwayml refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
s3_vectors fix(s3_vectors): embed registered-store ingests with the store's embedding model 2026-09-19 04:31:15 -07:00
sagemaker feat(sagemaker)!: inference components and OpenAI-compatible embeddings (#44985) 2026-10-12 22:25:52 +00:00
sail chore(lint): remove the LIT002 mutable-construction rule (#43971) 2026-10-01 12:24:02 -07:00
sambanova refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
sap refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
scaledown feat(scaledown): add native text provider support (#44168) 2026-10-10 14:01:17 -07:00
scaleway refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
searchapi feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
searxng feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
serper/search feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
snowflake refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
soniox refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
stability refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
strands_decider/decisions feat(strands_decider): call a Strands Decider on an AgentCore runtime ARN (#45678) 2026-10-09 22:51:19 -07:00
tavily/search feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
tencent refactor(anthropic): rename experimental_pass_through to pass_through (#43329) 2026-09-26 13:00:50 -07:00
tinyfish/search refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
together_ai refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
tool_loop feat(harness): add Harness.TOOL_LOOP, a minimal in-process tool-calling loop (#44391) 2026-10-03 17:33:01 +00:00
topaz feat(tokenizer): preserve Python defaults with opt-in Rust dispatch (#42174) 2026-09-22 04:41:11 +00:00
triton feat(tokenizer): preserve Python defaults with opt-in Rust dispatch (#42174) 2026-09-22 04:41:11 +00:00
typesafe/decisions refactor(decisions): dispatch /v1/decisions through provider configs and the shared HTTP handler (#45130) 2026-10-07 19:45:45 -07:00
v0 refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
valkey perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
vercel_ai_gateway refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
vertex_ai fix(vertex_ai): keep Gemini cache creation token count out of request kwargs (#46152) 2026-10-12 21:19:12 -07:00
vllm refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
volcengine refactor: expose public hidden_params accessors (#44668) 2026-10-07 00:01:33 -07:00
voyage feat(voyage): rebrand to VoyageAI by MongoDB and route MongoDB keys to ai.mongodb.com (#41812) 2026-10-08 13:12:47 -07:00
wandb chore(lint): remove the LIT002 mutable-construction rule (#43971) 2026-10-01 12:24:02 -07:00
watsonx refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
xai refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
xinference/image_generation feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
you_com feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
zai refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
__init__.py fix(cost): bill azure_ai claude web searches under deployment-owned pricing ids (#46135) 2026-10-12 19:40:53 -07:00
base.py refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
compaction.py feat(router): native compact-to-fit across conversation APIs (#42074) 2026-09-21 22:52:29 -07:00
custom_llm.py refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
maritalk.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
oss_decision.py feat: add Bespoke Nimble gateway and OSS classifier support (#44246) 2026-10-02 19:37:08 -07:00
README.md

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/.