scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103
litellm/litellm/llms
History
tin-berri d18e06f736
Merge pull request #41508 from BerriAI/litellm_1789600151_discover_context_limits 
feat(router): discover token limits for hosted OpenAI-compatible models
2026-09-16 20:29:57 -07:00
..
a2a Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_decrease_anys_opus5_r4 2026-09-03 01:27:33 +00:00
ai21/chat
aiml refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
aiohttp_openai/chat refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
amazon_nova refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
anthropic Merge pull request #41330 from BerriAI/litellm_team_model_max_budget_v2 2026-09-16 14:48:29 -07:00
apiserpent
aws_polly refactor(typing): replace Any with proven types in 89 more backend files 2026-09-02 23:08:42 +00:00
azure fix(azure_ai): strip the azure_ai/ prefix when a Responses call is remapped to azure 2026-09-16 16:49:29 -07:00
azure_ai refactor(responses): drop the api_base cast and mark the header merge mutable-ok 2026-09-16 15:45:50 -07:00
base_llm fix(guardrails): hold tool-call windows until the final scan and expose Bedrock streaming flags to the UI 2026-09-16 18:30:12 +00:00
baseten
bedrock Merge pull request #41513 from BerriAI/litellm_internal_copy_31400 2026-09-16 17:12:35 -07:00
bedrock_mantle style(responses_bridge): suppress type-discipline flags with reasons 2026-09-16 23:43:04 +00:00
black_forest_labs Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_async_remote_image_fetch 2026-09-05 00:37:19 -07:00
brave/search
bytez refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
cerebras fix(cerebras): add max_retries and extra_headers to get_supported_openai_params (#36601) 2026-08-25 14:10:56 -07:00
chatgpt Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_decrease_anys_opus5 2026-08-29 06:37:10 -07:00
clarifai/chat refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
cloudflare/chat
codestral/completion refactor(types): replace Any with precise types across 73 modules 2026-09-01 11:05:02 +00:00
cohere refactor(ocr): complete native lifecycle and preserve Azure auth (#40734) 2026-09-12 11:56:49 -07:00
cometapi refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
compactifai Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_decrease_anys_opus5 2026-08-29 06:37:10 -07:00
custom_httpx Merge pull request #34829 from max-sixty/bugfix/http-handler-del-closes-streaming-client 2026-09-16 13:39:04 -07:00
dashscope Merge remote-tracking branch 'origin/main' into litellm_dashscope_reasoning_effort 2026-09-16 14:41:08 -07:00
databricks fix(databricks): keep the Claude fallback when gating the anthropic thinking payload 2026-09-12 13:13:38 -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
deepgram
deepinfra refactor(types): replace Any with precise types across 73 modules 2026-09-01 11:05:02 +00:00
deepseek fix(anthropic): add the per-turn-control beta when a message carries output_config 2026-09-14 22:01:47 -07:00
deprecated_providers
docker_model_runner/chat
duckduckgo/search
e2b Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_decrease_anys_opus5 2026-08-29 06:03:33 -07:00
elevenlabs refactor(typing): replace Any with proven types in 42 more backend files 2026-09-02 15:35:01 +00:00
empower/chat
exa_ai/search
fal_ai refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
fastcrw
featherless_ai/chat
firecrawl
fireworks_ai Merge pull request #41335 from BerriAI/litellm_fireworks_dict_reasoning_effort 2026-09-16 13:12:37 -07:00
friendliai/chat
galadriel/chat
gdc chore(typing): clear 1.5k basedpyright Any errors across 54 files 2026-08-21 05:25:22 +00:00
gemini fix(vertex_ai): bill Gemini Omni Interactions usage and Veo sampleCount on passthrough 2026-09-15 22:42:27 +00:00
gigachat Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_decrease_anys_opus5_r4 2026-09-03 01:27:33 +00:00
github/chat
github_copilot fix(anthropic): add the per-turn-control beta when a message carries output_config 2026-09-14 22:01:47 -07:00
google_pse/search
gradient_ai/chat
groq refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
heroku/chat
hosted_vllm fix(hosted_vllm): reject image edit params vLLM-Omni ignores 2026-09-08 20:11:01 -07:00
huggingface refactor(typing): replace Any with proven types in 42 more backend files 2026-09-02 15:35:01 +00:00
hyperbolic
inception
infinity Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_decrease_anys_opus5 2026-08-29 06:03:33 -07:00
jina_ai test(cost): assert jina rerank spend at the registry rate 2026-09-10 07:04:19 -07:00
lambda_ai
langflow feat(agentcore-a2a): derive runtime session id from A2A message.contextId (#39371) 2026-09-02 12:40:24 -07:00
langgraph refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
lemonade refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
linkup
litellm_proxy fix(spend_tracking): honour the global litellm_proxy override when inferring a model group provider 2026-09-17 00:03:01 +00:00
llamafile/chat
lm_studio
manus
meta/realtime fix(realtime): keep a Muse turn active for turnless partials after speechEnd 2026-09-12 15:13:44 -07:00
meta_llama/chat
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(typing): replace Any with proven types in 42 more backend files 2026-09-02 15:35:01 +00:00
mistral fix(mistral): keep the deployment voice default and drop the unreachable api base fallback 2026-09-03 00:30:07 -07:00
modelscope
mongodb merge: resolve MongoDB sidecar staging conflicts 2026-09-08 13:59:56 -07:00
moonshot/chat fix(moonshot, together_ai): send the reasoning effort Kimi K3 accepts (#38611) 2026-08-27 20:46:46 -07:00
morph
nebius
nimble feat(search): add Nimble as a search provider (#36347) 2026-08-14 17:09:58 -07:00
nlp_cloud refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
novita/chat
nscale/chat
nvidia_nim fix(proxy): reject mixed NIM model groups and strip the deployment model before the group in /nvidia_nim URLs 2026-09-15 23:34:22 +00:00
nvidia_riva refactor(types): replace Any with real types across 54 more backend files 2026-08-29 19:00:43 +00:00
oci Merge pull request #39507 from BerriAI/litellm_fix_oci_streaming_chunk_ids 2026-09-11 11:46:35 -07:00
ollama perf: move Anthropic, Vertex Anthropic, Ollama and HF template fetches off the event loop (#40311) 2026-09-08 15:53:43 -07:00
oobabooga refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
openai Merge pull request #41201 from BerriAI/litellm_gemini_37_38_flash_no_minimal_thinking 2026-09-16 16:52:08 -07:00
openai_like refactor(router): move model info discovery provider set into openai_like module 2026-09-17 00:07:28 +00:00
openrouter refactor(typing): replace Any with proven types in 65 backend files 2026-09-02 09:11:36 +00:00
opensandbox Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_decrease_anys_opus5 2026-08-29 06:03:33 -07:00
ovhcloud
parallel_ai/search fix(search): forward search-tool params through the router, complete Parallel AI v1 param mapping (#37883) 2026-09-01 21:46:46 -07:00
pass_through refactor(typing): replace Any with proven types in 42 more backend files 2026-09-02 15:35:01 +00:00
perplexity chore: merge origin/litellm_internal_staging into litellm_decrease_anys_opus5_r4 2026-09-04 18:59:35 -07:00
petals refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
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(typing): drop the dead self guard in Predibase init and use a plain list factory 2026-09-04 19:42:37 -07:00
ragflow Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_decrease_anys_opus5_r4 2026-09-03 06:44:40 +00:00
recraft refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
reducto refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
replicate refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
runwayml refactor(types): replace Any with precise types across 73 modules 2026-09-01 11:05:02 +00:00
s3_vectors refactor(s3_vectors): embed search queries through the shared vector store executor 2026-09-02 19:26:31 -07:00
sagemaker feat(bedrock): thread aws_session_tags into STS AssumeRole 2026-09-09 12:37:36 -07:00
sambanova
sap refactor(types): replace Any with precise types across 73 modules 2026-09-01 11:05:02 +00:00
scaleway/audio_transcription
searchapi
searxng
serper/search
snowflake fix(async): move remote image fetches off the event loop for Snowflake, Bedrock invoke Claude, Mantle and Gemini 2026-09-04 17:48:56 -07:00
soniox refactor(typing): replace Any with proven types in 89 more backend files 2026-09-02 23:08:42 +00:00
stability refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
tavily/search
tencent fix(tencent): satisfy basedpyright budget in thinking mapping 2026-08-24 18:41:50 -03:00
tinyfish/search fix(search): propagate GET provider HTTP errors (#40779) 2026-09-11 14:07:32 -07:00
together_ai fix(moonshot, together_ai): send the reasoning effort Kimi K3 accepts (#38611) 2026-08-27 20:46:46 -07:00
topaz refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
triton refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
v0
valkey fix(vector-store): route embeddings through router 2026-09-01 15:33:18 -07:00
vercel_ai_gateway
vertex_ai Merge pull request #41201 from BerriAI/litellm_gemini_37_38_flash_no_minimal_thinking 2026-09-16 16:52:08 -07:00
vllm
volcengine
voyage fix(rerank): stamp a fresh response id when Voyage, watsonx, or Fireworks omit one 2026-09-13 01:34:22 -07:00
wandb fix(wandb): gate reasoning effort on model capabilities 2026-09-10 20:47:13 +02:00
watsonx fix(rerank): stamp a fresh response id when Voyage, watsonx, or Fireworks omit one 2026-09-13 01:34:22 -07:00
xai fix(xai): keep 'instructions' on the xAI Responses API so system messages survive web_search bridging 2026-09-16 01:35:13 +00:00
xinference/image_generation
you_com
zai
__init__.py fix(gemini): bill Google Maps grounding as its own SKU 2026-08-26 15:31:27 -07:00
base.py refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
custom_llm.py refactor(types): replace Any with real types across 178 backend files 2026-08-27 10:14:58 +00:00
maritalk.py
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/.