EvolutionaryScale · Rate Limits

Evolutionaryscale Rate Limits

EvolutionaryScale does not publish public rate-limit tables for the Forge API. The `esm` SDK's async clients (`async_generate`, `async_fold`, `batch_generate`, ...) imply server-side concurrency controls and request queueing. Limits are communicated to Forge beta participants individually and may be raised on request. AWS Marketplace deployments inherit AWS quota and instance-level concurrency limits.

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

It captures 7 rate-limit definitions, across the Forge Beta and AWS Marketplace tiers.

The profile also includes response codes documented for throttled and quotaExceeded.

Tagged areas include AI, Biology, Rate Limiting, and Proteins.

7 Limits Throttle: 429 Quota: 429
AIBiologyRate LimitingProteins

Limits

Concurrency and request-per-minute caps assigned per beta account.
Concurrency and request-per-minute caps assigned per beta account.
98B model — heavier per-request budget; limits set per account.
Effective rate limit is the throughput of the SageMaker / BioNeMo / NIM instance type and replica count.

Sources