Rate limits
Reads and writes are rate-limited per API key, with headers on every response telling you where you stand.
Rate limits are applied per API key using an atomic fixed-window counter.
| Endpoint type | Limit | Scope |
|---|---|---|
Read endpoints (GET) |
60 requests/min | per API key |
Write endpoints (POST to /quotes, /generations, /characters, /audio, /voices/clone) |
10 requests/min | per API key |
Headers
Every response includes your current standing:
| Header | Meaning |
|---|---|
X-RateLimit-Limit |
Max requests allowed in the window |
X-RateLimit-Remaining |
Requests left in the current window |
X-RateLimit-Reset |
Unix timestamp when the window resets |
Retry-After |
Seconds to wait — sent only on a 429 |
When you’re limited
Exceeding the limit returns 429 rate_limit_exceeded. Back off until the time in Retry-After, then retry.