Quick Start

Send your first chat completion in under a minute.

• A routing.run account
• An active Basic membership with a positive Routing balance
• An API key
• curl or any HTTP client

Make a chat completion request with curl:

curl https://api.routing.run/v1/chat/completions \  -H "Authorization: Bearer rk_live_your_api_key" \  -H "Content-Type: application/json" \  -d '{    "model": "kimi-k2.6",    "messages": [{"role": "user", "content": "Hello!"}]  }'

Install the OpenAI Python SDK and point it at routing.run:

pip install openai

from openai import OpenAI client = OpenAI(    api_key="rk_live_your_api_key",    base_url="https://api.routing.run/v1") response = client.chat.completions.create(    model="gpt-5.6-terra",    messages=[{"role": "user", "content": "Hello!"}]) print(response.choices[0].message.content)

routing.run is OpenAI- and Anthropic-compatible, so it drops into most coding agents and chat harnesses — set the base URL and your API key, then pick a currently available model from the catalog.

Claude CodeCodex DesktopOpenCodeKilo CodeHermesOOpenClawCursor

Point Claude Code at routing.run via the Anthropic-compatible base URL.

Environment

shell

export ANTHROPIC_BASE_URL="https://api.routing.run"export ANTHROPIC_API_KEY="rk_live_your_api_key" claude

• Browse the Model Catalog for all available models and pricing.
• Read the Models & Routing guide to understand how routing works.
• Explore the API Reference for full endpoint documentation.