Limits and billing

Request rate

Each key has a request budget per window. Every response says where you stand:

ratelimit-limit: 480
ratelimit-remaining: 479
ratelimit-reset: 60

Over the budget you get 429 rate_limited with retry-after. Reads have a larger budget than writes; one poll per job every few seconds stays far inside it.

Jobs in flight

A workspace may have only so many generation jobs queued or running at once. A submit past the cap is refused, not queued, and not charged: 429 queue_full, with your limits in details.generation_limits and a retry_after_seconds. Wait for a job to end, then submit the next; a worker pool sized to the limit keeps you under it.

{
  "error": {
    "code": "queue_full",
    "message": "Workspace generation queue is full. Wait for running jobs to complete before submitting more generation work.",
    "request_id": "req_0ee311b4334e4b118a94c7d1c48577fd",
    "category": "queue",
    "retryable": true,
    "retry_after_seconds": 30,
    "next_action": "retry_later"
  }
}

What a job costs

Each model row from the model endpoints carries its pricing; prices depend on quality, resolution and duration. The list prices are on API pricing, and every charge and refund shows up in Billing in the dashboard.

Running out of balance

A submit the balance cannot cover fails with 402 insufficient_credits and creates no job; a team workspace that has never been funded gets 402 organization_wallet_not_provisioned. With insufficient_credits, details says how much the request needed and how much was available, in dollars. Add funds in Billing; turning on auto top-up keeps long runs from stopping.

{
  "error": {
    "code": "insufficient_credits",
    "message": "Not enough credits for this request.",
    "request_id": "req_0ee311b4334e4b118a94c7d1c48577fd",
    "category": "quota",
    "retryable": false,
    "retry_after_seconds": null,
    "next_action": "add_funds",
    "details": {
      "required_usd": "0.29",
      "available_usd": "0.01"
    }
  }
}