ποΈ Integrate as a Model Provider
Quick Start for OpenAI-Compatible Providers
ποΈ Add OpenAI-Compatible Provider (JSON)
For simple OpenAI-compatible providers (like Hyperbolic, Nscale, etc.), you can add support by editing a single JSON file.
ποΈ Add Model Pricing & Context Window
To add pricing or context window information for a model, simply make a PR to this file:
ποΈ OpenAI
4 items
ποΈ OpenAI (Text Completion)
LiteLLM supports OpenAI text completion models
ποΈ OpenAI-Compatible Endpoints
Selecting openai as the provider routes your request to an OpenAI-compatible endpoint using the upstream
ποΈ Azure OpenAI
5 items
ποΈ Azure AI
9 items
ποΈ Vertex AI
11 items
ποΈ Google AI Studio
6 items
ποΈ Anthropic
LiteLLM supports all anthropic models.
ποΈ Tool Search
Tool search enables Claude to dynamically discover and load tools on-demand from large tool catalogs (10,000+ tools). Instead of loading all tool definitions into the context window upfront, Claude searches your tool catalog and loads only the tools it needs.
ποΈ AWS Sagemaker
LiteLLM supports All Sagemaker Huggingface Jumpstart Models
ποΈ Bedrock
13 items
ποΈ LiteLLM Proxy (LLM Gateway)
| Property | Details |
ποΈ Abliteration
Overview
ποΈ AI21
LiteLLM supports the following AI21 models:
ποΈ AI/ML API
https://aimlapi.com/
ποΈ Aleph Alpha
LiteLLM supports all models from Aleph Alpha.
ποΈ Amazon Nova
| Property | Details |
ποΈ Anyscale
https://app.endpoints.anyscale.com/
ποΈ Apertis AI (Stima API)
Overview
ποΈ Baseten
LiteLLM supports both Baseten Model APIs and dedicated deployments with automatic routing.
ποΈ Black Forest Labs Image Generation
Black Forest Labs provides state-of-the-art text-to-image generation using their FLUX models.
ποΈ Black Forest Labs Image Editing
Black Forest Labs provides powerful image editing capabilities using their FLUX models to modify existing images based on text descriptions.
ποΈ Bytez
LiteLLM supports all chat models on Bytez!
ποΈ Cerebras
https://inference-docs.cerebras.ai/api-reference/chat-completions
ποΈ Chutes
Overview
ποΈ Clarifai
Anthropic, OpenAI, Qwen, xAI, Gemini and most of Open soured LLMs are Supported on Clarifai.
ποΈ Cloudflare Workers AI
https://developers.cloudflare.com/workers-ai/models/text-generation/
ποΈ Codestral API [Mistral AI]
Codestral is available in select code-completion plugins but can also be queried directly. See the documentation for more details.
ποΈ Cohere
API KEYS
ποΈ CometAPI
LiteLLM supports all AI models from CometAPI. CometAPI provides access to 500+ AI models through a unified API interface, including cutting-edge models like GPT-5, Claude Opus 4.1, and various other state-of-the-art language models.
ποΈ CompactifAI
https://docs.compactif.ai/
ποΈ Crusoe
Overview
ποΈ Custom API Server (Custom Format)
Call your custom torch-serve / internal LLM APIs via LiteLLM
ποΈ Dashscope API (Qwen models)
https://dashscope.console.aliyun.com/
ποΈ Databricks
LiteLLM supports all models on Databricks
ποΈ DataRobot
LiteLLM supports all models from DataRobot. Select datarobot as the provider to route your request through the datarobot OpenAI-compatible endpoint using the upstream official OpenAI Python API library.
ποΈ Deepgram
LiteLLM supports Deepgram's /listen endpoint.
ποΈ DeepInfra
https://deepinfra.com/
ποΈ Deepseek
https://deepseek.com/
ποΈ Docker Model Runner
Overview
ποΈ ElevenLabs
ElevenLabs provides high-quality AI voice technology, including speech-to-text capabilities through their transcription API.
ποΈ EmpirioLabs AI
Overview
ποΈ Fal AI
Fal AI provides fast, scalable access to state-of-the-art image generation models including FLUX, Stable Diffusion, Imagen, and more.
ποΈ Featherless AI
https://featherless.ai/
ποΈ Fireworks AI
We support ALL Fireworks AI models, just set fireworks_ai/ as a prefix when sending completion requests
ποΈ FriendliAI
We support ALL FriendliAI models, just set friendliai/ as a prefix when sending completion requests
ποΈ Galadriel
https://docs.galadriel.com/api-reference/chat-completion-API
ποΈ Github
https://github.com/marketplace/models
ποΈ GitHub Copilot
https://docs.github.com/en/copilot
ποΈ GMI Cloud
Overview
ποΈ ChatGPT Subscription
Use ChatGPT Pro/Max subscription models through LiteLLM with OAuth device flow authentication.
ποΈ GradientAI
https://digitalocean.com/products/gradientai
ποΈ Groq
https://groq.com/
ποΈ Helicone
Overview
ποΈ Heroku
Provision a Model
ποΈ HuggingFace
2 items
ποΈ Hyperbolic
Overview
ποΈ Inception
Overview
ποΈ Infinity
| Property | Details |
ποΈ Jina AI
https://jina.ai/embeddings/
ποΈ Lambda AI
Overview
ποΈ LangGraph
Call LangGraph agents through LiteLLM using the OpenAI chat completions format.
ποΈ Lemonade
Lemonade Server is an OpenAI-compatible local language model inference provider optimized for AMD GPUs and NPUs. The lemonade litellm provider supports standard chat completions with full OpenAI API compatibility.
ποΈ Llamafile
LiteLLM supports all models on Llamafile.
ποΈ LlamaGate
Overview
ποΈ LM Studio
https://lmstudio.ai/docs/basics/server
ποΈ Manus
Use Manus AI agents through LiteLLM's OpenAI-compatible Responses API.
ποΈ Meta Model API
| Property | Details |
ποΈ Meta Llama
| Property | Details |
ποΈ Milvus - Vector Store
Use Milvus as a vector store for RAG.
ποΈ Mistral AI API
https://docs.mistral.ai/api/
ποΈ MiniMax
Overview
ποΈ Moonshot AI
Overview
ποΈ Morph
LiteLLM supports all models on Morph
ποΈ Nebius AI Studio
https://docs.nebius.com/studio/inference/quickstart
ποΈ NLP Cloud
LiteLLM supports all LLMs on NLP Cloud.
ποΈ NanoGPT
Overview
ποΈ Novita AI
| Property | Details |
ποΈ Nscale (EU Sovereign)
https://docs.nscale.com/docs/inference/chat
ποΈ Nvidia NIM
2 items
ποΈ Nvidia Riva (Speech-to-Text)
LiteLLM supports NVIDIA Riva for speech-to-text via /audio/transcriptions. Works with both the NVCF-hosted Riva endpoint (e.g. Parakeet on build.nvidia.com) and self-hosted Riva deployments.
ποΈ Oracle Cloud Infrastructure (OCI)
LiteLLM supports the following models for OCI on-demand GenAI API.
ποΈ Ollama
LiteLLM supports all models from Ollama
ποΈ OpenRouter
LiteLLM supports all the text / chat / vision / embedding models from OpenRouter
ποΈ Sarvam.ai
LiteLLM supports all the text models from Sarvam ai
ποΈ π OVHCloud AI Endpoints
Leading French Cloud provider in Europe with data sovereignty and privacy.
ποΈ Perplexity AI
2 items
ποΈ Petals
Petals//github.com/bigscience-workshop/petals
ποΈ Poe
Overview
ποΈ PublicAI
Overview
ποΈ Predibase
LiteLLM supports all models on Predibase
ποΈ Pydantic AI Agents
Call Pydantic AI Agents via LiteLLM's A2A Gateway.
ποΈ RAGFlow
Litellm supports Ragflow's chat completions APIs
ποΈ Recraft
https://www.recraft.ai/
ποΈ Replicate
LiteLLM supports all models on Replicate
ποΈ RunwayML
2 items
ποΈ SambaNova
https://cloud.sambanova.ai/
ποΈ SAP Generative AI Hub
LiteLLM supports SAP Generative AI Hub's Orchestration Service.
ποΈ Scaleway
LiteLLM supports all models available on Scaleway Generative APIs β.
ποΈ Stability AI
https://stability.ai/
ποΈ Synthetic
Overview
ποΈ Snowflake Cortex
LiteLLM supports all models on the Snowflake Cortex REST API, including models from Anthropic (Claude), OpenAI (GPT), Meta (Llama), Mistral, DeepSeek, and Snowflake.
ποΈ Tencent TokenHub
https://www.tencentcloud.com/products/tokenhub
ποΈ Tensormesh
Overview
ποΈ Together AI
LiteLLM supports all models on Together AI.
ποΈ Topaz
| Property | Details |
ποΈ Triton Inference Server
LiteLLM supports Embedding Models on Triton Inference Servers
ποΈ v0
Overview
ποΈ Vercel AI Gateway
Overview
ποΈ vLLM
2 items
ποΈ Volcano Engine (Volcengine)
https://www.volcengine.com/docs/82379/1263482
ποΈ Voyage AI
https://docs.voyageai.com/embeddings/
ποΈ Weights & Biases Inference
https://weave-docs.wandb.ai/quickstart-inference
ποΈ WatsonX
2 items
ποΈ xAI
2 items
ποΈ Xiaomi MiMo
https://platform.xiaomimimo.com/#/docs
ποΈ Xinference [Xorbits Inference]
https://inference.readthedocs.io/en/latest/index.html
ποΈ Z.AI (Zhipu AI)
https://z.ai/