Platform
Rate limits & quotas
Requests are limited per minute and metered in credits against your workspace plan.
Plans
| Plan | Requests / minute | Credits / month |
|---|---|---|
| Free | 60 | 1,000 |
| Starter | 300 | 25,000 |
| Scale | 1,200 | 250,000 |
| Enterprise | Custom | Custom |
Credits
| Endpoint | Credits per call |
|---|---|
| POST /denoise | 1 |
| POST /denoise/batch | 1 |
| GET /models, /sample, /health | 0 |
When the monthly credits run out, calls return 402 quota_exhausted until the next period or an upgrade.
Response headers
| Header | Meaning |
|---|---|
| RateLimit-Limit | Requests allowed per minute for this token. |
| RateLimit-Remaining | Requests left in the current window. |
| RateLimit-Reset | Seconds until the window resets. |
| Retry-After | On 429 only: seconds to wait before retrying. |
| X-Request-Id | Correlates the call with the gateway request log. |
| X-Gateway-Upstream-Ms | Time the model service took, in milliseconds. |
| X-NS-Stats / X-NS-Batch | Noise Suppressor processing stats for single and bulk calls. |
Size limits
One file up to 100 MB per /denoise call. Up to 25 files and 200 MB per /denoise/batch call. Larger requests return 413 payload_too_large.