vLLM

vLLM OpenAI-Compatible Server

OpenAI-compatible REST API exposed by `vllm serve`. Endpoints include /v1/chat/completions, /v1/completions, /v1/embeddings, /v1/score, /v1/audio/transcriptions, /v1/audio/translations, /v1/realtime (WebSocket), /tokenize, /detokenize, and /generative_scoring. Authentication via the --api-key flag set on server start; clients can use the official OpenAI Python library unmodified, with vLLM-specific extensions passed via extra_body.

GitHub

Documentation

📖
Documentation
https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html

Other Resources

🔗
GitHub
https://github.com/vllm-project/vllm
🔗
OpenAICompat
https://platform.openai.com/docs/api-reference
🔗
APIsJSON
https://raw.githubusercontent.com/api-evangelist/vllm/refs/heads/main/apis.yml

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/openai-compatible"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

API entry from apis.yml

apis.yml Raw ↑ 
aid: vllm:openai-compatible
name: vLLM OpenAI-Compatible Server
description: OpenAI-compatible REST API exposed by `vllm serve`. Endpoints include /v1/chat/completions,
  /v1/completions, /v1/embeddings, /v1/score, /v1/audio/transcriptions, /v1/audio/translations, /v1/realtime
  (WebSocket), /tokenize, /detokenize, and /generative_scoring. Authentication via the --api-key flag
  set on server start; clients can use the official OpenAI Python library unmodified, with vLLM-specific
  extensions passed via extra_body.
humanURL: https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html
baseURL: http://localhost:8000/v1
tags:
- Chat
- Completions
- Embeddings
- Audio
- Score
- OpenAI-Compatible
properties:
- type: Documentation
  url: https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html
- type: GitHub
  url: https://github.com/vllm-project/vllm
- type: OpenAICompat
  url: https://platform.openai.com/docs/api-reference