Reference

Billing & plans

Every plan meters usage in words per month, with a per-request cap and a requests-per-minute throughput limit. These numbers are the single source of truth used everywhere else in these docs.

Starter

$0/mo

1 req/min
3 req/day per key
1,500 words/request cap
20,000 words/mo
90 requests/mo
1 concurrent async job
1 team seat

Growth

$49/mo

15 req/min
500 req/day per key
2,000 words/request cap
200,000 words/mo
5,000 requests/mo
3 concurrent async jobs
3 team seats

Scale

priority

$199/mo

60 req/min
5,000 req/day per key
4,000 words/request cap
1,200,000 words/mo
50,000 requests/mo
10 concurrent async jobs
10 team seats

Rate limits & quotas

Plan	Requests/min	Requests/day	Requests/mo	Max words/request	Monthly word cap	Priority processing
Starter	1	3	90	1,500	20,000	No
Growth	15	500	5,000	2,000	200,000	No
Scale	60	5,000	50,000	4,000	1,200,000	Yes

requestsPerDay is the primary Starter-plan control lever — it, not the monthly cap, is usually what a free account hits first. Priority processing on async jobs (POST /v1/jobs) is enforced via a dedicated concurrency allowance per plan (see “concurrent async jobs” above): higher tiers can have more of their jobs in flight at once rather than sharing one undifferentiated queue.

Quota exceeded response

Once consumed.words reaches limits.monthlyWords, further generation requests return:

429

{
  "error": {
    "code": "QUOTA_EXCEEDED",
    "message": "Monthly word quota exceeded for plan 'growth'. Upgrade your plan or wait for the next billing period.",
    "requestId": "req_f6e5d4c3b2",
    "details": {
      "monthlyWords": 200000,
      "consumedWords": 200000,
      "periodEnd": "2026-10-01T00:00:00.000Z"
    }
  }
}