Nscale · Rate Limits

Nscale Rate Limits

Nscale enforces per-account rate limits on serverless inference, typically expressed as requests per minute (RPM) and tokens per minute (TPM) per model, with limits scaling by account tier and usage. GPU compute is governed by organization-level capacity quotas rather than request-rate limits. Specific per-model values are not reconciled in this artifact.

Nscale Rate Limits is the machine-readable rate-limit profile for Nscale on the APIs.io network, conforming to the API Commons Rate Limits specification.

It captures 4 rate-limit definitions, measuring requests, tokens, concurrency, and gpu_capacity.

The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include AI, GPU, Inference, Serverless, and Cloud Compute.

4 Limits Throttle: 429
AIGPUInferenceServerlessCloud ComputeRate LimitingQuotasThrottling

Limits

Requests Per Minute (RPM) account
requests
see provider documentation
Per-model RPM on serverless inference, varies by tier and model.
Tokens Per Minute (TPM) account
tokens
see provider documentation
Per-model TPM on serverless inference, varies by tier and model.
Concurrent Requests account
concurrency
see provider documentation
Maximum in-flight inference requests per account/key.
GPU Compute Quota organization
gpu_capacity
see provider documentation
Organization-level GPU/instance capacity quota for compute provisioning, not a request rate.

Policies

Tiered Limits
Limits raise as accounts move from free to paid usage and via Enterprise agreements.
Backoff Strategy
Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses.

Sources