API Documentation

OpenAI-compatible API for distributed inference on Apple Silicon.

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.repogen.xyz/v1",
    api_key="rg_live_xxxxx"
)

response = client.chat.completions.create(
    model="gpt-oss-20b",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

Authentication

Use Bearer token in the Authorization header.

Chat Completions

Parameters

Response

{
  "id": "chatcmpl-abc123",
  "model": "gpt-oss-20b",
  "choices": [{
    "message": {
      "role": "assistant",
      "content": "Hello!"
    }
  }],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 9
  }
}

Streaming

Set stream: true for SSE responses.

data: {"choices":[{"delta":{"content":"Hello"}}]}
data: {"choices":[{"delta":{"content":"!"}}]}
data: [DONE]

Models

Prices per million tokens.

Billing

Rate Limits

Errors

For Providers

Run inference on your Mac and earn USDC.

# Download CLI
curl -L https://github.com/topguyaii/repogen-inference/releases/download/v0.1.0-alpha/repogen-macos-arm64.tar.gz | tar xz
sudo mv repogen /usr/local/bin/

# Verify & run
repogen doctor
repogen models download gpt-oss-20b
repogen start --foreground