Rate Limits
To ensure fair usage and platform stability, rate limits are applied to all API requests.
Limits
API Key rate limits
- 1200 tokens per minute
IP rate limits
- 2400 tokens per minute
- 400 requests per 10 seconds exceeding this limit ban for 5 minutes
Request Weight
Each request has its own weight. The weight may be dynamically adjusted depending on the request content and complexity.
For example:
- Simple requests may consume fewer tokens
- Complex requests may consume more tokens
- Limits may change without prior notice to maintain system stability
Rate Limit Headers
When rate limiting is applied, the following headers are returned:
| Header | Description | Example |
|---|---|---|
| RateLimit-Limit | Maximum number of tokens allowed in the current period | 1200 |
| RateLimit-Remaining | Remaining tokens in the current period | 875 |
| RateLimit-Reset | Time when the rate limit resets (UNIX timestamp in milliseconds) | 1773649807000 |