API Overview

rbee provides a REST API compatible with the OpenAI API specification, making it easy to integrate with existing tools and libraries.

Base URL

http://localhost:8080/v1

Authentication

API requests require a bearer token:

curl -H "Authorization: Bearer YOUR_API_KEY" \
  http://localhost:8080/v1/models

Core Endpoints

List Models

GET /v1/models

Returns all available models in your rbee instance.

Chat Completions

POST /v1/chat/completions

Generate chat completions using a specified model.

Request body:

{
  "model": "llama-3.1-8b",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is the capital of France?"}
  ],
  "temperature": 0.7,
  "max_tokens": 150
}

Streaming Responses

Enable streaming by setting stream: true:

{
  "model": "llama-3.1-8b",
  "messages": [...],
  "stream": true
}

Rate Limits

Default rate limits:

• 100 requests per minute per API key
• 1000 tokens per second per model

Error Handling

All errors follow the standard format:

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found"
  }
}