OpenRouter

​

At a glance

• Availability: Experimental (how to enable).
• Authentication: API key.
• Connection: The key comes from OPENROUTER_API_KEY.
• Provider documentation: Authentication reference.

​

Credentials

Set these per environment. See Connect an integration.

​

Setup

1. Create an OpenRouter account: Go to https://openrouter.ai and sign up or sign in. Some models offer free variants for testing; paid models require purchasing credits under Settings → Credits.
2. Create an API key: Open https://openrouter.ai/settings/keys, click ‘Create Key’, and optionally set a credit limit for the key.
3. Store the key: Copy the key and add it to your .env file as OPENROUTER_API_KEY=sk-or-…
4. Verify access: Run the List Models tool to confirm the key works, then try a chat completion with a model like openai/gpt-4o-mini.

​

Provider notes

• Model IDs are namespaced as vendor/model, e.g. anthropic/claude-sonnet-4
• Chat completions consume prepaid credits; use the Get Generation tool to inspect the exact cost of a request
• The Get Credits endpoint requires a management key per OpenRouter’s docs - a regular inference key may be rejected there

Provider API reference.

​

Tools

​

Verify the connection

Call a read tool such as openrouter__list_models with arguments for your account. Confirm that the result comes from the intended account or workspace before enabling write tools.