ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
74496eefea
litellm/litellm/llms
History
Ishaan Jaff 1249385a99
[Feat] GEMINI CLI - Add Token Counter for VertexAI Models (#13558) 
* add VertexAIModelInfo

* working API call to vertex ai

* add count_tokens MODE

* _construct_url

* test_vertex_ai_gemini_token_counting_with_contents
2025-08-12 20:53:47 -07:00
..
ai21/chat
aiohttp_openai/chat
anthropic [Feat] GEMINI CLI Integration - Add /countTokens endpoint support (#13545) 2025-08-12 16:19:58 -07:00
azure [Bug Fix]: Azure OpenAI GPT-5 max_tokens + reasoning param support (#13510) 2025-08-11 15:40:53 -07:00
azure_ai Litellm dev 06 18 2025 p1 (#11872) 2025-06-18 21:24:36 -07:00
base_llm [Feat] GEMINI CLI Integration - Add /countTokens endpoint support (#13545) 2025-08-12 16:19:58 -07:00
bedrock [Feat] Add Streaming support + Docs for bedrock gpt-oss model family (#13346) 2025-08-12 08:39:36 -07:00
bytez ruff check ./litellm --fix 2025-07-12 11:04:02 -07:00
cerebras
clarifai
cloudflare/chat
codestral/completion
cohere Add Hosted VLLM rerank provider integration (#12738) 2025-07-18 10:55:50 -07:00
cometapi feat: add CometAPI provider support with chat completions and streaming (#13458) 2025-08-11 18:06:37 -07:00
custom_httpx [Bug Fix] Gemini-CLI Integration - ensure tool calling works as expected on generateContent (#13189) 2025-07-31 16:42:57 -07:00
dashscope Added dashscope (alibaba's cloud - qwen) as a provider (#12361) 2025-07-10 18:09:26 -07:00
databricks [Bug Fix] [Bug]: New Databricks Foundation Models databricks-gpt-oss-20b and databricks-gpt-oss-120b failed with error: litellm.APIConnectionError: 'signature' (#13318) 2025-08-05 17:46:40 -07:00
datarobot/chat Add support for DataRobot as a provider in LiteLLM (#10385) 2025-06-02 08:37:21 -07:00
deepgram [Feat] Add Eleven Labs - Speech To Text Support on LiteLLM (#12119) 2025-06-27 17:50:49 -07:00
deepinfra/chat
deepseek
deprecated_providers
elevenlabs [Feat] Add Eleven Labs - Speech To Text Support on LiteLLM (#12119) 2025-06-27 17:50:49 -07:00
empower/chat
featherless_ai/chat
fireworks_ai Add Claude 4 Sonnet & Opus, DeepSeek R1, and fix Llama Vision model pricing configurations (#11339) 2025-06-03 20:39:47 -07:00
friendliai/chat
galadriel/chat
gemini [Feat] GEMINI CLI - Add Token Counter for VertexAI Models (#13558) 2025-08-12 20:53:47 -07:00
github/chat
github_copilot fix: add X-Initiator header for GitHub Copilot to reduce premium requests (#13016) 2025-07-28 09:55:24 -07:00
gradient_ai/chat Add digitalocean provider (#12169) 2025-08-09 16:26:33 -07:00
groq ruff fix 2025-07-11 21:59:10 -07:00
hosted_vllm Add Hosted VLLM rerank provider integration (#12738) 2025-07-18 10:55:50 -07:00
huggingface Revert "Revert "fix tests (#12286)"" 2025-07-03 12:08:27 -07:00
hyperbolic Revert "Litellm dev 07 21 2025 p1 (#12848)" 2025-07-22 18:28:36 -07:00
infinity
jina_ai feat(JinaAI): support multimodal embedding models (#13181) 2025-08-05 19:21:56 -07:00
lambda_ai Revert "Litellm dev 07 21 2025 p1 (#12848)" 2025-07-22 18:28:36 -07:00
litellm_proxy/chat LiteLLM SDK <-> Proxy improvement (don't transform message client-side) + Bedrock - handle qs:.. in base64 file data + Tag Management - support adding public model names (#11908) 2025-06-19 22:34:18 -07:00
llamafile/chat
lm_studio
meta_llama/chat [Feat] Enable Tool Calling for meta_llama (#11895) 2025-06-19 13:44:22 -07:00
mistral [Bug Fix] Mistral Tool Calling - Grammar error: at 3(11): failed to compile JSON schema (#13389) 2025-08-07 13:50:22 -07:00
moonshot/chat Fix MoonshotChatConfig to address limitations of kimi-thinking-preview model by excluding additional parameters (#12772) 2025-07-19 15:10:57 -07:00
morph fix morph api tests 2025-07-22 18:44:44 -07:00
nebius
nlp_cloud
novita/chat
nscale/chat
nvidia_nim #response_format NVIDIA-NIM add response_format to OpenAI parameters mapping (#12003) 2025-06-24 09:44:35 -07:00
oci Fix OCI streaming (#13437) 2025-08-11 18:04:58 -07:00
ollama Fix default parameters for ollama-chat (#12201) 2025-07-01 17:59:04 -07:00
oobabooga
openai [Bug Fix] Responses API - Responses API failed if input containing ResponseReasoningItem (#13465) 2025-08-09 11:20:34 -07:00
openai_like
openrouter Openrouter - filter out cache_control flag for non-anthropic models (allows usage with claude code) (#12850) 2025-07-21 22:15:48 -07:00
perplexity add Perplexity citation annotations support (#13225) 2025-08-02 08:47:35 -07:00
petals
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
recraft [Feat] Add Google AI Studio Imagen4 model family (#13065) 2025-07-28 21:25:40 -07:00
replicate
sagemaker Feat(bedrock): support api key authentication for AWS Bedrock API (#12426) (#12495) 2025-07-10 15:12:17 -07:00
sambanova Feat/sambanova embeddings (#13308) 2025-08-12 17:15:26 -07:00
snowflake
together_ai
topaz
triton
v0 feat: add v0 provider support (#12751) 2025-07-18 18:26:44 -07:00
vertex_ai [Feat] GEMINI CLI - Add Token Counter for VertexAI Models (#13558) 2025-08-12 20:53:47 -07:00
vllm Refactor: bedrock passthrough fixes - migrate to Passthrough SDK (#12089) 2025-06-26 22:51:35 -07:00
voyage/embedding
watsonx Revert "Litellm dev 07 21 2025 p1 (#12848)" 2025-07-22 18:28:36 -07:00
xai [Bug Fix] grok-4 does not support the stop param (#12646) 2025-07-16 09:19:25 -07:00
xinference/image_generation [Feat] Add XInference Image Generation API Provider (#12439) 2025-07-08 21:17:38 -07:00
__init__.py Gemini - web search cost tracking + Update max output tokens for nova models 2025-06-05 23:25:18 -07:00
base.py Gemini - web search cost tracking + Update max output tokens for nova models 2025-06-05 23:25:18 -07:00
baseten.py
custom_llm.py Add bridge for /chat/completion -> /responses API (#11632) 2025-06-11 22:20:18 -07:00
maritalk.py
ollama_chat.py Ollama Chat - parse tool calls on streaming (#11171) 2025-05-27 16:14:49 -07:00
README.md
volcengine.py Anthropic /v1/messages - Custom LLM Server support (#12016) 2025-06-24 22:00:44 -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/.