Rate Limits and Quotas

Understand and work within API limits.

Rate Limits

Limits depend on your plan:

Plan	Requests/min	Tokens/min
Free	10	10,000
Pro	60	100,000
Team	120	500,000
Enterprise	Custom	Custom

Rate Limit Headers

Responses include rate limit info:

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 45
X-RateLimit-Reset: 1640000000

Handling Rate Limits

When rate limited, you receive:

{
  "error": {
    "code": "rate_limit_exceeded",
    "message": "Rate limit exceeded. Try again in 30 seconds."
  }
}

Best practices:

1. Implement exponential backoff
2. Cache responses when possible
3. Batch requests where applicable

Quotas

Monthly token quotas by plan:

• Free: 100K tokens/month
• Pro: 10M tokens/month
• Team: 50M tokens/month
• Enterprise: Custom