ποΈ /a2a - A2A Agent Gateway
ποΈ /assistants
OpenAI has deprecated the Assistants API. It will shut down on August 26, 2026.
ποΈ /audio/transcriptions
Overview
ποΈ /audio/speech
Overview
ποΈ /batches
3 items
ποΈ /containers
Manage OpenAI code interpreter containers (sessions) for executing code in isolated environments.
ποΈ /containers/files
Manage files within Code Interpreter containers. Files are created automatically when code interpreter generates outputs (charts, CSVs, images, etc.).
ποΈ /chat/completions
4 items
ποΈ /completions
Overview
ποΈ /converse
Call Bedrock's /converse endpoint through LiteLLM Proxy.
ποΈ /embeddings
Quick Start
ποΈ /files
2 items
ποΈ /fine_tuning
2 items
ποΈ /evals
LiteLLM Proxy supports OpenAI's Evaluations (Evals) API, allowing you to create, manage, and run evaluations to measure model performance against defined testing criteria.
ποΈ /generateContent
Use LiteLLM to call Google AI's generateContent endpoints for text generation, multimodal interactions, and streaming responses.
ποΈ /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.
ποΈ /invoke
Call Bedrock's /invoke endpoint through LiteLLM Proxy.
ποΈ /interactions
| Feature | Supported | Notes |
ποΈ /v1beta/agents (Gemini Managed Agents)
LiteLLM now supports the Google AI Studio Managed Agents API. Create, manage, and run custom agents through LiteLLM.
ποΈ /memory
CRUD endpoints for storing and retrieving user/team-scoped memory entries on the LiteLLM proxy. Use these to persist conversation context, agent memory, team playbooks, or any key-value data scoped to users and teams.
ποΈ /images/edits
LiteLLM provides image editing functionality that maps to OpenAI's /images/edits API endpoint. Now supports both single and multiple image editing.
ποΈ Image Generations
Overview
ποΈ [BETA] Image Variations
OpenAI's /image/variations endpoint is now supported.
ποΈ /videos
| Feature | Supported |
ποΈ /vector_stores/\{vector_store_id\}/files
Vector store files represent the individual files that live inside a vector store.
ποΈ /vector_stores - Create Vector Store
Create a vector store which can be used to store and search document chunks for retrieval-augmented generation (RAG) use cases.
ποΈ /vector_stores/search - Search Vector Store
Search a vector store for relevant chunks based on a query and file attributes filter. This is useful for retrieval-augmented generation (RAG) use cases.
ποΈ /mcp - Model Context Protocol
18 items
ποΈ /v1/messages
3 items
ποΈ Token Counting
Overview
ποΈ /v1/messages/count_tokens
Overview
ποΈ /moderations
Usage
ποΈ /ocr
| Feature | Supported |
ποΈ Pass-through Endpoints (Anthropic SDK, etc.)
16 items
ποΈ /rag/ingest
All-in-one document ingestion pipeline: Upload β Chunk β Embed β Vector Store
ποΈ /rag/query
RAG Query endpoint: Search Vector Store β (Rerank) β LLM Completion
ποΈ /realtime
Use this to loadbalance across Azure + OpenAI + xAI and more.
ποΈ /realtime - WebRTC Support
Connect to the Realtime API via WebRTC from browser/mobile clients. LiteLLM handles auth; audio streams directly to OpenAI/Azure.
ποΈ /rerank
LiteLLM Follows the cohere api request / response for the rerank api
ποΈ /responses
LiteLLM provides an endpoint in the spec of OpenAI's /responses API
ποΈ Prompt Management with Responses API
Use LiteLLM Prompt Management with /v1/responses by passing promptid and optional promptvariables.
ποΈ /responses/compact
Compress conversation history using OpenAI's /responses/compact endpoint.
ποΈ /search
14 items
ποΈ /skills - Anthropic Skills API
| Feature | Supported |