Limits by Plan
- Pro ($30/mo): 300 requests per minute
- Creator ($50/mo): 600 requests per minute
These are global rate limits that apply across all endpoints combined.
Per-Endpoint Limits
Some resource-intensive endpoints have additional lower limits:
- Voice sessions: 10 concurrent sessions
- File uploads (knowledge base): 30 requests per minute
- Character creation: 60 requests per minute
- WebSocket connections: 50 concurrent (Pro), 100 concurrent (Creator)
Rate Limit Headers
Every API response includes rate limit information in the headers:
X-RateLimit-Limit: your total allowed requests per minuteX-RateLimit-Remaining: how many requests you have left in the current windowX-RateLimit-Reset: Unix timestamp when the window resets
Handling Rate Limits
When you exceed the limit, the API returns HTTP 429 Too Many Requests with a Retry-After header indicating how many seconds to wait. Best practices:
- Implement exponential backoff: wait, then retry with increasing delays
- Monitor the headers: check
X-RateLimit-Remainingbefore making batches of requests - Queue requests: if you need to send many messages, queue them and respect the per-minute window
- Cache responses: avoid re-fetching data that does not change frequently (character details, user profiles)