Skip to main contentTo ensure stability and fair access for all users, llm.kiwi implements rate limits across all API endpoints.
Tiered Limits
Limits are applied based on your current account tier.
| Tier | Tokens Per Minute (TPM) | Requests Per Minute (RPM) |
|---|
| Free | 40,000 | 3 |
| Developer | 200,000 | 50 |
| Scale | 1,000,000 | 500 |
| Enterprise | Custom | Custom |
Handling Rate Limits
When a rate limit is reached, the API will return a 429 Too Many Requests response.
Best Practices
- Exponential Backoff: If you receive a 429, wait for a short period before retrying. Increase the wait time exponentially with each subsequent failure.
- Request Optimization: Batch tasks when possible and avoid redundant calls.
- Token Management: Monitor your token usage in the response headers to anticipate limits.
Increasing Your Limits
If your application requires higher throughput, you can upgrade your plan in the Billing Dashboard or contact our support team for enterprise-grade custom limits. 