generated: '2026-07-19'
method: searched
source: https://docs.inceptionlabs.ai/get-started/rate-limits
scope: per-minute
note: >-
  Requests can be rate limited based on usage and GPU availability; contact
  support to raise limits. Limits are enforced per minute across three tiers.
rate_limits:
- tier: Free
  requests_per_minute: 100
  input_tokens_per_minute: 100000
  output_tokens_per_minute: 10000
- tier: Pay As You Go
  requests_per_minute: 1000
  input_tokens_per_minute: 1000000
  output_tokens_per_minute: 100000
- tier: Enterprise
  requests_per_minute: 10000
  input_tokens_per_minute: 10000000
  output_tokens_per_minute: 1000000
  note: 10,000+ / 10M+ / 1M+ (floor; negotiated higher)
signaling:
  headers: []
  note: >-
    No documented RateLimit / X-RateLimit response headers; a 429 Too Many
    Requests (type rate_limit_error) signals throttling. Clients should
    implement exponential backoff on 429 and 503.