Skip to main content
API requests are rate limited per account to ensure system stability.

​
Generation limits

You can create up to 10 generations per 60 seconds, with only 1 concurrent generation allowed.

​
Endpoint limits

​
GET /v1/status
string
60 requests per minute.
​
GET /v1/data/account
string
60 requests per minute.
​
GET /v1/data/list/image
string
30 requests per minute.
​
GET /v1/image-generation/:id
string
10 requests per minute.
​
POST /v1/image-generation/:modelIdentifier
string
1 concurrent request maximum.

​
Handling rate limits

ImplementationDescription
Monitor remaining requests.Check the X-RateLimit-Remaining header to track your usage.
Implement exponential backoff.When rate limited (429 status), wait before retrying with increasing delays.
Use reset timestamp.Check X-RateLimit-Reset to know exactly when to retry.
Queue requests.Implement client-side queuing to stay within rate limits.
Log request IDs.Always log X-Request-ID for debugging failed or rate-limited request.