Rate Limits
Updated at:
Memory API request frequency limits
Memory API rate limits are at the Alibaba Cloud account level.
| API | Limit |
|---|---|
| All endpoints | Up to 3000 QPM total |
| Factual memory add | 120 QPM |
| Factual memory search | 300 QPM |
When exceeded, HTTP 429 is returned. Use exponential backoff for retries.
To request a higher rate limit, submit a ticket.
ImportantSee Billing for pricing details.
Is this page helpful?