generated: '2026-08-12'
method: searched
source: >-
  https://platform.gist.ai/docs/gist-content-api,
  https://platform.gist.ai/reference/get_v1-questions-recommended,
  openapi/gist-answers-api-openapi.yml
note: >-
  Gist publishes the rate-limit RESPONSE HEADERS for the Answers API but not the numeric limits —
  every reference page says limits are "based on your organization's settings". The one published
  number is the Content API default. Both facts are recorded; nothing is estimated.
headers:
  limit: X-RateLimit-Limit
  remaining: X-RateLimit-Remaining
  reset: X-RateLimit-Reset
  reset_format: Unix timestamp when the rate limit resets
  retry_after: not documented
exhausted:
  status: 429
  body: '{"error": "...", "message": "...", "statusCode": 429}'
rate_limits:
- scope: per-organization
  api: Gist Answers API (Prorata API Service)
  window: null
  limit: null
  burst: null
  headers: [X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset]
  status_on_exhaustion: 429
  docs: https://platform.gist.ai/reference/get_v1-questions-recommended
  note: >-
    Configured per organization and not published. Applies to POST /v1/chat,
    POST /v1/chat/completions, the chat citations/attributions/response reads, both question
    operations, all three thread operations and both summarization operations. GET /v1/health and
    GET / are public and declare no 429.
- scope: per-publisher-group-api-key
  api: Gist Content API
  window: 1 minute
  limit: 10
  burst: null
  headers: []
  status_on_exhaustion: 429
  docs: https://platform.gist.ai/docs/gist-content-api
  note: >-
    "The default rate limit is 10 requests per minute. If you need a higher rate limit, please
    contact our support team." The ingest docs do not state which response headers are returned.
limit_count: 2
numeric_limits_published: 1