Adept · Rate Limits

Adept Rate Limits

Adept does not operate a public commercial API and therefore does not publish API-level rate limits. Practical rate limits for users of Adept's open-source models (Fuyu-8B, Persimmon-8B) are determined by the customer's own self-hosted inference stack or by their chosen third-party inference provider, not by Adept.

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

It captures 3 rate-limit definitions, measuring not_offered, downloads, and requests.

The profile also includes 1 backoff/retry policy defined and response codes documented for throttled.

Tagged areas include AI, Agents, Foundation Models, Action Models, and Open Source.

3 Limits Throttle: 429
AIAgentsFoundation ModelsAction ModelsOpen SourceRate LimitingQuotasThrottling

Limits

Commercial API not_applicable
not_offered
not offered
Adept does not operate a commercial inference API to rate-limit.
Hugging Face Downloads huggingface_account
downloads
per Hugging Face Hub policy
Standard Hugging Face anonymous / authenticated download limits apply when fetching weights.
Self-Hosted Inference deployment
requests
bounded by self-hosted GPU capacity
Throughput is determined by the customer's chosen hardware.

Policies

Self-Host Capacity Planning
Size GPU deployments per Fuyu-8B / Persimmon-8B model footprint and expected concurrency.

Sources