OpenRouter

Connect OpenRouter to use supported models for AI chat, Message Templates, and flow blocks. OpenRouter generates or analyzes text; a separate email or text-message integration sends completed messages.

  • You want to use OpenRouter models for AI chat, Message Templates, or flow-based generation and analysis.
  • You want to choose a supported model or let OpenRouter route each request automatically.
  • Create or copy an OpenRouter API key from OpenRouter key settings.
  • Confirm your role can create integrations. Without that permission, New Integration is not shown.
  • Confirm Use AI on this account is on. Only the owner or members with settings edit permission can change it.
Choose OpenRouter in the AI integration wizard.
  1. Go to Integrations → AI.
  2. Select New Integration, then choose OpenRouter.
Review the blank OpenRouter connection fields before verifying an API key.
  1. Review the Name, which defaults to “OpenRouter,” and enter your OpenRouter API Key.
  2. Select Verify API Key. This saves the integration, asks OpenRouter to validate the key, and loads the available models.
  3. After validation succeeds, optionally choose a Default Model, then select Save & Continue.
  1. On the Verify step, review Credentials stored. Before the second check, it confirms only that credentials are saved. To run another live OpenRouter validation, select Check credentials. After it succeeds, the status reports “These credentials work.” Then select Done.

Default Model appears after Verify API Key succeeds. Drip Drop lists Auto (best available) first, followed by supported OpenRouter models.

  • In an AI flow block, leave Model (optional) set to Provider default to let OpenRouter route the request through Auto (best available).
  • In an AI flow block, choose a listed model under Model (optional) when that block should use a specific model.
  • Drip Drop lists OpenRouter's auto-router first, followed by models from Anthropic, Google, Meta Llama, Mistral AI, and OpenAI.
Note
AI chat requires a model that supports tool calling. Support varies across OpenRouter models and routes. If OpenRouter rejects a request, choose a different model from the Model menu in AI chat or check the model page on OpenRouter.
  • In AI chat, choose OpenRouter as the provider and select a tool-capable model under Model. Ask about your account or the documentation; suggested changes wait for your approval.
  • In Message Templates, open AI Assistant, choose OpenRouter, and ask for a draft, rewrite, or tone change. Apply or dismiss each proposed change from its preview.
  • In the Flow Editor, select the OpenRouter integration to generate message text or analyze content. A separate email or text-message integration sends completed messages.
API key does not validate
  • Confirm the OpenRouter API key is active, paste it again under OpenRouter API Key, and select Verify API Key.
  • Check the OpenRouter account for permission restrictions before retrying.
Models do not appear or stop working
  • If verification succeeds but no models appear, try again later. Key verification can succeed even when model discovery fails.
  • If a model selected in a flow stops working, choose another option under Model (optional), or choose Provider default to return to Auto (best available).
Rate limits, credits, and provider errors
  • If an AI flow fails, check the OpenRouter account for available credits, rate limits, model access, or a temporary service issue.
  • If OpenRouter rejects the selected model, choose another model in the AI flow block and retry.
  • Flow Editor: Build automated workflows with the visual editor and AI flow blocks.