API Reference

> Complete reference for ProxyLLM API endpoints. Public inference endpoints are OpenAI-compatible unless noted.

//Base URL

OpenAI-compatible with /v1bash

https://proxyllm.eu/v1

//Authentication

Every request requires an API key. Use the Authorization header for OpenAI-compatible endpoints.

OpenAI-compatiblebash

Authorization: Bearer <your-api-key>

//POST /v1/chat/completions

OpenAI-compatible chat completions. Supports streaming, multi-turn messages, and the public model aliases enabled in the model catalog.

>Request Parameters

Tham số	Kiểu	Bắt buộc	Mô tả
model	string	Yes	Model ID to use, for example gpt-5.5 or claude-opus-4.7.
messages	array	Yes	Array of role/content message objects.
stream	boolean	No	When true, the response is streamed as server-sent events. Default: false.
temperature	number	No	Sampling temperature from 0 to 2. Higher values are more random. Default: 1.
max_tokens	integer	No	Maximum number of output tokens to generate.
reasoning_effort	string	No	Reasoning effort for thinking models: low, medium, or high.

>Request Example

cURLbash

curl https://proxyllm.eu/v1/chat/completions \
  -H "Authorization: Bearer $PROXYLLM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4.7",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": false
  }'

>Response Example

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1714000000,
  "model": "claude-opus-4.7",
  "choices": [{
    "index": 0,
    "message": { "role": "assistant", "content": "Hello! How can I help you today?" },
    "finish_reason": "stop"
  }],
  "usage": { "prompt_tokens": 10, "completion_tokens": 12, "total_tokens": 22 }
}

//GET /v1/models

List all available public model aliases for the current API key.

cURLbash

curl https://proxyllm.eu/v1/models \
  -H "Authorization: Bearer $PROXYLLM_API_KEY"