OpenRouter API URL

Most OpenAI-compatible clients want the versioned base URL. Chat completions are POST https://openrouter.ai/api/v1/chat/completions. The model list is GET https://openrouter.ai/api/v1/models. Key limits are GET https://openrouter.ai/api/v1/key. Generation stats are GET https://openrouter.ai/api/v1/generation?id=…

A minimal chat call

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openrouter/free","messages":[{"role":"user","content":"Reply in one sentence."}]}'

In the official OpenAI SDKs, set baseURL or base_url to https://openrouter.ai/api/v1 and pass the OpenRouter key as the API key. Optional headers HTTP-Referer and X-OpenRouter-Title are how OpenRouter attributes the call on public app rankings.

Which URL goes in which client

Claude Code’s cookbook tells you to include the scheme and to stop at /api. Adding /v1 there breaks that client. The OpenAI SDK wants the opposite: include /v1.

How to use it the first time

• Create an account at openrouter.ai/sign-in.
• Add credits if you will call a paid slug. Free slugs work at a $0 balance that is not negative.
• Create a key. It begins with sk-or-v1-.
• Put the base URL and key in the client, then set a model slug from the catalog.