Black Forest Labs · Rate Limits

Black Forest Labs Rate Limits

BFL's primary throughput control is async generation with a polling_url returned per request. Specific RPS or concurrent job caps are not publicly documented; large customers should consult sales for negotiated throughput.

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

It captures 2 rate-limit definitions, measuring concurrent_jobs and requests.

The profile also includes 3 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include AI, Image Generation, Flux, Open Weights, and BFL.

2 Limits Throttle: 429
AIImage GenerationFluxOpen WeightsBFLRate LimitingQuotasThrottling

Limits

Async Job Concurrency account
concurrent_jobs
not publicly documented
Use the returned polling_url; do not construct your own polling URL.
HTTP Requests account
requests
not publicly documented
Standard 429 backoff applies.

Policies

Backoff Strategy
Clients should implement exponential backoff with jitter and honor any Retry-After header.
Polling Discipline
Always use the polling_url returned in the response rather than constructing one client-side.
Regional Routing
Choose the EU or US regional endpoint to control data residency and latency.

Sources