Rate Limits
Current Rate Limits
| Endpoint | Limit |
|---|---|
/v1/chat/completions |
500/day, 10/minute |
| All other endpoints | 50,000/day, 100/minute |
Limits are applied per IP address. Limits may be higher for authenticated users.
Need Higher Limits?
Contact us at hello@llm.vin with:
- Your use case details
- Expected request volume
- Timeline requirements
Related Documentation
- Models - Available models and capabilities
- Chat Completions - API usage and streaming