specification: API Commons Rate Limits
specificationVersion: '0.1'
schema: https://raw.githubusercontent.com/api-evangelist/interface-research/main/schema/api-commons.yml#/$defs/RateLimits
provider: Akool
providerId: akool
created: '2026-07-11'
modified: '2026-07-11'
reconciled: false
tags:
- AI Avatars
- Video Generation
- Generative AI
- Rate Limiting
- Quotas
description: >-
  Akool does not publish fixed numeric per-minute request-rate limits for the
  OpenAPI. In practice, throughput is governed by two things: your plan's
  monthly credit allowance (every generation deducts credits) and your plan's
  concurrent-generation limit (Starter allows roughly 2-4 concurrent jobs, with
  higher and custom concurrency on Pro Max, Business, and Enterprise). Because
  generation is asynchronous - create a task, then poll by id or await a webhook
  - clients naturally pace themselves against the concurrency ceiling rather
  than a per-second cap. Bearer tokens expire and must be refreshed (error code
  1101 signals an expired or invalid token).
notes: >-
  Numeric per-account or per-endpoint request limits are not documented as of
  the review date. The binding constraints are credit balance and concurrent-job
  count per plan. Verify concurrency limits per tier and any burst limits on the
  pricing and API-pricing pages during reconciliation. Generated resources are
  retained for 7 days.
sources:
- https://docs.akool.com/authentication/usage
- https://docs.akool.com/ai-tools-suite/error-code
- https://akool.com/pricing
responseCodes:
  success: 1000
  authInvalidOrExpired: 1101
  authEmpty: 1102
  accountBanned: 1200
limits:
- name: OpenAPI Request Rate
  scope: account
  metric: requests
  limit: not published
  notes: No fixed numeric per-minute request-rate limit is documented for the OpenAPI.
- name: Concurrent Generations
  scope: account
  metric: concurrent-jobs
  limit: per plan (~2-4 on Starter, higher / custom on upper tiers)
  notes: The primary throttle. Asynchronous jobs run against a per-plan concurrency ceiling.
- name: Monthly Credit Allowance
  scope: account
  metric: credits
  limit: per plan
  notes: Every generation deducts credits; exhausting the allowance blocks further generation until topped up.
- name: Token Lifetime
  scope: account
  metric: token
  limit: expires
  notes: Bearer tokens from /getToken expire; refresh on error code 1101. The x-api-key method avoids token refresh.
policies:
- name: Asynchronous Create-then-Poll
  description: Generation endpoints return a task id immediately; clients poll the info endpoint by id or receive an encrypted webhook on completion rather than holding a long request open.
- name: Credit Metering
  description: Requests are metered by credits consumed per operation and per output setting (resolution, length), not by a request-count quota.
- name: Backoff Strategy
  description: Clients should poll with a reasonable interval and exponential backoff, and prefer webhooks over tight polling loops to reduce load.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com