<Info>This API is in beta. Endpoints, fields, and behavior may still change, so avoid depending on it in production.</Info>

Removes every queued message and lifts any pause, so the next message you send runs as soon as the AI is free. With keep_pr_watch=true, queued PR Watch runs stay in the queue, and if any remain the queue keeps its pause. The turn that's already running isn't affected. Stop it with Stop generation.

A message that was just taken off the queue to run is cancelled too, if its turn hasn't started yet.

A collaborator in the editor can send a queued message into the turn that's running. While that's happening the message can't be changed or removed. Clearing the queue is refused until it finishes, unless you pass keep_sent=true.

With keep_sent=true, messages already sent into the chat stay in the queue and still run, even after the turn they were sent into ends, and the request is never refused for a message being sent. Until that behavior reaches your account, keep_sent has no effect and the clear works as without it.

This is limited to 60 requests per minute per app for each workspace's personal API keys, so every key in a workspace shares one allowance. Every endpoint that changes the queue shares it. Some workspaces have a different limit.

<Note>This endpoint accepts a personal API key belonging to a user with editor access to the app. A read-only key is refused, and workspace API keys are not accepted.</Note>

<Warning>The response includes fields beyond the ones documented here. Don't rely on undocumented response fields, as they can change at any time.</Warning>

{
  "items": [
    {
      "branch_id": "68f1a2b3c4d5e6f708192a3b",
      "content": "Add a contact form to the home page",
      "created_at": "2026-10-05T14:30:00.123456+00:00",
      "id": "3b9d2f6e-8c41-4a7e-9f05-1d2c3b4a5e6f"
    }
  ]
}