Fireworks AI

Open-model requests are transient and no-training by default, but stored-response and proprietary partner routes can differ.

Plan Scope

Fireworks AI open-model inference and Responses API; proprietary model partners, explicit logging opt-ins, and advanced features can differ.

Prompt Retention

Open-model prompts and generations exist only in volatile memory for the request by default; prompt caches may remain in volatile memory for several minutes. Responses API stores full conversation data for 30 days when store=true, which is the default.

Response Retention

Same default ZDR for ordinary inference and 30-day stored conversation policy for Responses API.

Ordinary Logging

Token counts and service-delivery metadata are logged without content under ZDR. FireOptimizer and similar advanced features can collect content only after explicit opt-in.

Model Training

Fireworks does not log or store open-model prompt or generation data for training without explicit opt-in; proprietary model partner terms must be checked separately.

Product Improvement

Metadata can support service delivery and improvement, while content use requires an explicit logging or feature opt-in under the published open-model policy.

Human Or Operator Access

Default open-model payloads are not written to persistent storage. Stored Responses conversations and opted-in feature data can be accessed for service, support, security, and legal purposes.

Subprocessors And Routing

Fireworks hosts open models and may offer partner models under separate model-provider terms; its subprocessors are documented through the trust center.

Deletion Controls

Responses users can set store=false or immediately delete a stored response by ID; otherwise conversation data expires after 30 days.

Caveat

“ZDR by default” does not describe the Responses API default, which is store=true. Always set store=false when using Responses and review proprietary-model terms.