name: Magic Hour rate limits
generated: '2026-09-03'
method: searched
source: https://docs.magichour.ai/billing/subscription-pricing.md and https://docs.magichour.ai/get-started/quick-start.md
limit_count: 3
limits:
- scope: per-account (Creator plan)
  type: concurrency
  limit: 3
  unit: concurrent generations
- scope: per-account (Pro plan)
  type: concurrency
  limit: 5
  unit: concurrent generations
- scope: per-account (Business plan)
  type: concurrency
  limit: unlimited
  unit: concurrent generations
response_signaling:
  status_code: 429
  headers: []
  note: 429 Too Many Requests is documented with retry-with-exponential-backoff guidance, but no X-RateLimit-*,
    RateLimit-* or Retry-After response headers are documented. 402 signals credit exhaustion and 403 signals a
    plan-gated model/resolution — both act as spend guards distinct from throttling.
note: The published throttle model is plan-tier concurrency on generation jobs rather than requests-per-window;
  no per-second/minute request quota is documented.