Can one key call both the Model API and the Agent API?

Keys are scoped by permission, and the permissions are listed side by side when you create a key: models:invoke for the Model API, runs:write and runs:read for the Agent API, account:read for your balance.

Separate keys per product and per service are the safer pattern: each has its own rate limit, its own log trail, and you can revoke one without touching the other. Both APIs need the same X-Clatter-Account header.

See API keys.

Good to know#

• If calls fail unexpectedly, check status.clatterlabs.com before debugging further.
• Retry only 429 and 5xx errors, with backoff; honour Retry-After when it's sent. Which errors to retry
• Your key's account is responsible for your end users' text under the Abuse policy. What it means for apps

Still need help?#

• General support: support@clatterlabs.com or team@clatterlabs.xyz
• Infrastructure questions, or permanent deletion of your data (your whole account or one service): infrastructure@clatterlabs.xyz

We usually reply within the first hour, and always within 24 hours. A full support team is with you.