🗃️ /a2a - A2A Agent Gateway
3 items
📄️ /assistants
OpenAI has deprecated the Assistants API. It will shut down on August 26, 2026.
🗃️ /audio
2 items
🗃️ /batches
2 items
📄️ /containers
Manage OpenAI code interpreter containers (sessions) for executing code in isolated environments.
📄️ /containers/files
Manage files within Code Interpreter containers. Files are created automatically when code interpreter generates outputs (charts, CSVs, images, etc.).
🗃️ /chat/completions
4 items
📄️ /completions
Overview
📄️ /converse
Call Bedrock's /converse endpoint through LiteLLM Proxy.
📄️ /embeddings
Quick Start
🗃️ /files
2 items
🗃️ /fine_tuning
2 items
📄️ /generateContent
Use LiteLLM to call Google AI's generateContent endpoints for text generation, multimodal interactions, and streaming responses.
📄️ /guardrails/apply_guardrail
Use this endpoint to directly call a guardrail configured on your LiteLLM instance. This is useful when you have services that need to directly call a guardrail.
📄️ /invoke
Call Bedrock's /invoke endpoint through LiteLLM Proxy.
📄️ /interactions
| Feature | Supported | Notes |
🗃️ /images
3 items
📄️ /videos
| Feature | Supported |
📄️ /vector_stores/\{vector_store_id\}/files
Vector store files represent the individual files that live inside a vector store.
🗃️ /mcp - Model Context Protocol
5 items
📄️ /v1/messages
Use LiteLLM to call all your LLM APIs in the Anthropic v1/messages format.
📄️ /v1/messages/count_tokens
Overview
📄️ /moderations
Usage
📄️ /ocr
| Feature | Supported |
🗃️ Pass-through Endpoints (Anthropic SDK, etc.)
14 items
🗃️ /rag
2 items
📄️ /realtime
Use this to loadbalance across Azure + OpenAI.
📄️ /rerank
LiteLLM Follows the cohere api request / response for the rerank api
📄️ /responses
LiteLLM provides an endpoint in the spec of OpenAI's /responses API
🗃️ /search
10 items
📄️ /skills - Anthropic Skills API
| Feature | Supported |
🗃️ /vector_stores
2 items