Skip to content
GhostMind

Rate Limits

Rate Limit Headers

Responses include headers indicating your rate limit status:

HeaderDescription
X-RateLimit-LimitMaximum requests per window
X-RateLimit-RemainingRemaining requests in current window
X-RateLimit-ResetUnix timestamp when the window resets

Rate Limit Response

When rate limited, you receive a 429 response:

{
  "error": {
    "message": "Rate limit exceeded. Try again in 60 seconds.",
    "type": "rate_limit_exceeded"
  }
}

Endpoint-Specific Limits

EndpointLimit
/v1/chat/completionsConfigurable per instance
/v1/audio/generationsConfigurable per instance
/v1/audio/transcriptionsConfigurable per instance

Quota vs Rate Limit

  • Rate limit — Short-term request frequency (per minute)
  • Quota — Long-term usage limits (per day/month, per workspace)

Both are enforced independently. Hitting either will result in a 429 response.

Next Steps

  • Errors — Error reference
  • Usage — Monitor your usage