Featherless AI · Rate Limits

Featherless Rate Limits

Featherless AI does not meter tokens. Instead each subscription plan grants a fixed number of concurrent connections (concurrency limit), and tokens are unlimited within that concurrency. Smaller models allow higher effective throughput than larger ones. The number of in-flight requests an account may run is therefore the primary limit; additional requests beyond the plan concurrency are rejected until a slot frees. Live concurrency state can be observed via the account concurrency stream.

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

It captures 3 rate-limit definitions, measuring connections, tokens, and parameters.

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

Tagged areas include AI, LLM, Inference, Serverless, and Open Models.

3 Limits Throttle: 429
AILLMInferenceServerlessOpen ModelsRate LimitingQuotasThrottling

Limits

Concurrent Connections account
connections
see plan (Basic 2, Premium 4, agent/business 8 per unit)
Maximum simultaneous in-flight inference requests per account/plan.
Tokens account
tokens
unlimited within plan concurrency
Featherless bills a flat monthly subscription; tokens are not metered.
Model Size account
parameters
see plan (Basic up to 15B; Premium any size)
Larger models reduce effective per-connection throughput.

Policies

Concurrency-Based Limiting
Throughput is governed by the number of concurrent connections in the plan rather than by token quotas; excess concurrent requests are rejected with HTTP 429 until a slot is available.
Backoff Strategy
Clients should implement exponential backoff with jitter and honor Retry-After when concurrency is saturated.

Sources