Rate limits
- OpenAPI 3.1.0 document: https://api.rollstack.com/public/v1/openapi.json
- The whole reference in Markdown: https://docs.rollstack.com/llms-full.txt
- An index of the reference: https://docs.rollstack.com/llms.txt
Each API key may make 120 requests a minute. Calls that cost far more than a read have lower limits of their own, counted per user across all their keys and AI clients:
| Calls | Limit |
|---|---|
| Messages to the slides agent | 6 a minute |
| Exports and slide images | 10 a minute |
| Datasheet data reads | 30 a minute |
| Report viewer slide loads (MCP) | 60 a minute |
| Email sends, test sends included | 5 a minute |
| LLM provider saves | 10 a minute for the organization |
Responses report how much of the key's per-minute limit is left, so a client can slow down before it gets a 429: RateLimit-Limit, RateLimit-Remaining, RateLimit-Reset (seconds until the minute resets) and RateLimit-Policy. The lower limits above aren't in these headers. Past any limit, calls answer 429 with a Retry-After header: wait that long before calling again, whatever RateLimit-Remaining says. An MCP tool call past one of the lower limits returns an error result instead, with the rate-limit-exceeded code and a message that says how long to wait.