Rate Limits

Limits

StarUnion rate-limits on two dimensions: per-account and per-model. The default account RPM (requests per minute) is 60 and TPM (tokens per minute) is 100,000. Complete identity verification in the console or contact sales to raise them.

Response Headers

Each response returns the following headers to help you monitor your quota:

• X-RateLimit-Limit-Requests — request ceiling for the current window
• X-RateLimit-Remaining-Requests — requests still available
• X-RateLimit-Reset-Requests — reset time (seconds)
• X-RateLimit-Limit-Tokens — token ceiling
• X-RateLimit-Remaining-Tokens — tokens still available