Rate Limits by Plan
| Plan | Per Hour | Per Day | Notes |
|---|---|---|---|
| Starter | 5 | 20 | Starter-tier models only |
| Basic | 30 | 200 | All models |
| Pro | 60 | 500 | All models |
| VIP | 100 | 1,000 | All models + API access |
| Elite | ∞ | ∞ | No limits |
Rate Limit Headers
Every API response includes headers showing your current status:Handling Rate Limit Errors
When you exceed the rate limit, the API returns429 Too Many Requests:
retry_after field tells you how many seconds until the limit resets.
Best Practices
Implement exponential backoff
Implement exponential backoff
Don’t hammer the API after a 429. Wait, then retry with increasing delays:
Monitor remaining limits proactively
Monitor remaining limits proactively
Check
X-RateLimit-Remaining-Hour in each response and slow down when you’re close to the limit, rather than waiting for a 429.Batch where possible
Batch where possible
For bulk tasks (e.g. generating 100 product images), spread requests over time. A VIP user can do 100/hour — you can saturate this with a simple queue.
Consider Elite for automation
Consider Elite for automation
If you’re building a production service with unpredictable load, the Elite plan’s unlimited rate is designed for that use case.
Auth Endpoint Limits
Authentication endpoints have stricter rate limits to prevent abuse:| Endpoint | Limit |
|---|---|
POST /auth/login | 10 requests/min per IP |
POST /auth/register | 10 requests/min per IP |
POST /auth/forgot-password | 3 requests/hour per IP |

