generated: '2026-07-18'
method: searched
source: https://api.compresr.ai/api/billing/tiers
docs: https://compresr.ai/docs/api-reference/rate-limits
model: tier-based per-API-key; enforced per-minute and per-day; separate request and token quotas
enforcement:
  status: 429 Too Many Requests
  header: Retry-After (seconds)
  signal_headers:
  - X-RateLimit-Limit-Minute
  - X-RateLimit-Remaining-Minute
  - X-RateLimit-Limit-Day
  - X-RateLimit-Remaining-Day
  - X-RateLimit-Tier
tiers:
- tier: tier1
  min_monthly_tokens: 0
  max_api_keys: 2
  limit_count: 60      # requests per minute
  rpm: 60
  tpm: 250000
  rpd: 5000
- tier: tier2
  min_monthly_tokens: 1000000
  max_api_keys: 4
  limit_count: 120
  rpm: 120
  tpm: 500000
  rpd: 10000
- tier: tier3
  min_monthly_tokens: 5000000
  max_api_keys: 8
  limit_count: 250
  rpm: 250
  tpm: 1000000
  rpd: 50000
- tier: tier4
  min_monthly_tokens: 25000000
  max_api_keys: 16
  limit_count: 500
  rpm: 500
  tpm: 2000000
  rpd: 100000
- tier: tier5
  min_monthly_tokens: 100000000
  max_api_keys: 32
  limit_count: 1000
  rpm: 1000
  tpm: 4000000
  rpd: 5000000
notes: >-
  Numbers are live from GET /api/billing/tiers (base scale). Faster models consume a
  higher tier_scale (latte_v2 = x2, some x5) which multiplies effective throughput per
  the scale_limits table on the same endpoint.