Rate Limits
Claude API rate limits — requests per minute, token limits, and how to handle 429 errors gracefully.
Status code: 429 Too Many Requests. Header: Retry-After (seconds). Strategy: Exponential backoff with jitter. Per-key RPM: Configurable from dashboard.
Rate Limiting
The ClaudeStore gateway applies per-tier rate limits to ensure fair usage and service stability. When you exceed your limit, the API returns a 429 status code along with a Retry-After header.
Limits by plan
| Plan | RPM | TPM (input) | TPM (output) |
|---|---|---|---|
| Starter ($5) | 60 | 40,000 | 8,000 |
| Pro ($50) | 300 | 200,000 | 40,000 |
| Business ($500) | 1,000 | 600,000 | 120,000 |
| Team ($1,250) | 2,000 | 1,200,000 | 240,000 |
RPM = requests per minute. TPM = tokens per minute.
Response headers
x-ratelimit-limit-requests— your RPM capx-ratelimit-remaining-requests— requests remaining in the current windowx-ratelimit-reset-requests— seconds until the window resetsretry-after— seconds to wait before retrying after a 429
Handling 429 Responses
- Implement exponential backoff (start at 1s, double each retry)
- Respect
Retry-Afterheaders when present - Queue requests in your application layer
- Consider using smaller models for high-throughput scenarios
If you consistently hit rate limits, contact support to discuss higher limits for your use case.