Platform
Rate Limits
Request limits, what happens when you hit them, and how to request higher limits.
For detailed rate limit information including current limits by tier, see the Inference API rate limits page.
What happens when you hit a limit
You'll receive a 429 Too Many Requests response. Back off and retry with exponential backoff.
Deployment-specific limits
Self-serve deployments on a single GPU have inherent throughput limits. If traffic exceeds capacity, requests slow down and eventually return 429s. For higher throughput, see Scale to Production.
Requesting higher limits
If you need higher rate limits, talk to the team.