Getting started
Rate limits
Per-workspace request rates, in-flight caps, and monthly quotas.
Limits apply per workspace, across all billable operations.
Request rate
| Plan | Requests per minute | In-flight commit/illuminate |
|---|---|---|
| Free | 60 | 2 |
| Pro | 600 | 10 |
The per-minute limit is a token bucket, so short bursts above the sustained rate are absorbed. The in-flight cap bounds concurrent heavy operations (commit and illuminate) separately.
Exceeding either answers 429 with a Retry-After header:
{
"detail": "rate limited",
"code": "rate_limited"
}Honor Retry-After and retry with backoff. SDK clients surface the header on
the raised error.
Monthly quotas
| Quota | Free | Pro |
|---|---|---|
| Commit operations | 1,000 | 1,000,000* |
| Search operations | 5,000 | 1,000,000* |
| Illuminate operations | 50 | 1,000,000* |
| Namespaces | 3 | 50 |
| Blob storage | 1 GiB | 50 GiB |
*Pro operations are metered per use; 1,000,000 is a runaway-protection ceiling on each counter, not a purchased allowance.
A request past an exhausted quota answers 402 before the request body is
even parsed. Every LLM-consuming path is metered, not just commit: file
uploads, document reprocessing, and connector ingestion meter as commit;
manual consolidation and automation refresh meter as illuminate.
Usage is visible in the dashboard, and upgrading lifts the caps immediately.
Service backstops
Independent of plan limits, the service sheds excess load with 503 +
Retry-After rather than queuing, and any single request is bounded to 300
seconds. Treat 503 as retryable with backoff.