API Overview

Base URL

https://api.ru-llm.relay2.xyz

Replace this with your self-hosted gateway URL if applicable.

API surfaces

ru-llm exposes two fully compatible API surfaces on the same gateway:

Surface	Base path	Protocol
OpenAI-compatible	/v1	OpenAI Chat Completions API
Anthropic-compatible	/v1	Anthropic Messages API

The surface is determined by the endpoint you call, not by configuration.

Authentication

All requests require an sk-ru-… API key. Both surfaces accept either header:

Authorization: Bearer sk-ru-YOUR_KEY

x-api-key: sk-ru-YOUR_KEY

Create and manage keys in the console → API Keys.

Endpoints

OpenAI-compatible

Method	Path	Description
POST	/v1/chat/completions	Chat completion (streaming or non-streaming)
GET	/v1/models	List available models

Anthropic-compatible

Method	Path	Description
POST	/v1/messages	Messages API (streaming or non-streaming)
GET	/v1/models	List available models

Cross-dialect routing

Cross-dialect

The gateway translates between API dialects automatically. You can send a Claude model ID to /v1/chat/completions, or a GPT/Gemini model ID to /v1/messages — the proxy translates both the request and the response, including streaming events.

This means your existing OpenAI SDK code can access Claude models without any changes to the SDK — just point base_url at the gateway and switch the model ID.

Content types

All request and response bodies are JSON (Content-Type: application/json). Streaming responses use text/event-stream (Server-Sent Events).

Versioning

• OpenAI surface: no version header required.
• Anthropic surface: pass anthropic-version: 2023-06-01 (or later) in request headers.