New

    Introducing AutoEvals: Find the right model for your task

    ZERO DATA RETENTION POLICY

    This Zero Data Retention Policy ("ZDR Policy") describes how Inference R&D, Inc., doing business as Inference.net ("Inference.net", "we", "us" or "our"), handles the content of inference requests sent to our serverless inference API (the "API"). It is incorporated into, and subject to, our Terms of Service, and supplements our Privacy Policy.

    1. DEFINITIONS

    "Customer Content" means the inputs you submit to the API, such as prompts, messages, images, files and tool definitions, and the outputs the API returns to you.

    "Zero Data Retention" or "ZDR" means that Customer Content is processed transiently, only as needed to fulfill the request, is not logged, and is not retained after processing of the request is complete, except as described in this ZDR Policy.

    2. ENABLING ZDR

    Any team account on the Inference.net platform can enable ZDR by turning on the Zero Data Retention (ZDR) setting in its team settings. No separate agreement is required. Customers who want contractual terms may request a data processing agreement by contacting us.

    ZDR applies to requests received after the setting takes effect, which may take a short period. It does not remove data recorded before it took effect. You may request deletion of that data by contacting us; deleted data may remain in backups for a limited period until it is overwritten in the normal backup cycle.

    While ZDR is enabled, features that require retaining Customer Content, such as batch and asynchronous processing and file uploads, may be unavailable, and requests to them may be rejected. Inference.net determines which models, endpoints and features are eligible for ZDR and may update eligibility from time to time.

    3. OUR COMMITMENT

    For requests from a team with ZDR enabled:

    • Customer Content is processed transiently and is not retained after processing of the request is complete.
    • Customer Content is not logged.
    • Customer Content is not used to train, fine-tune, evaluate or benchmark any model.
    • Performance caches, such as prompt caches, may hold intermediate model computations derived from Customer Content. Cached data is not stored as text, is used only to serve requests, and is overwritten as the cache is reused.

    We use commercially reasonable technical and organizational measures to implement ZDR. If we discover that Customer Content was retained or logged contrary to this ZDR Policy, we will delete it promptly after discovery.

    4. DATA WE RETAIN

    To operate, secure and bill for the API, we retain operational metadata about each request that is not intended to include Customer Content. This includes account and API key identifiers, the model requested, timestamps, token counts, latency, status and error codes, and billing records. We may also retain security and abuse-prevention records, and audit logs as required by our security and legal obligations.

    5. EXCLUSIONS

    ZDR does not apply to:

    • requests not authenticated with an API key belonging to a team that has ZDR enabled;
    • content you choose to store, such as files, datasets, evaluation results and fine-tuning data;
    • requests served by models hosted by third-party providers, which are subject to that provider's data handling terms;
    • information you send to us outside the API, such as through support requests or in account, project or API key names; and
    • Customer Content we reasonably believe is needed to investigate or respond to a security incident, fraud, or a violation of our Terms of Service, retained only as long as necessary for that purpose.

    Inference.net is not in breach of this ZDR Policy to the extent that any logging, retention or disclosure of Customer Content results from settings you choose, including disabling ZDR, from third-party products or models you choose to use, or from actions taken at your written direction. Enabling ZDR does not change your obligations under our Terms of Service, and you remain responsible for your use of the API and the content you submit.

    6. SUBPROCESSORS

    We use third-party infrastructure providers to operate the API. They process Customer Content only to provide services to us and are bound by written confidentiality, security and data protection obligations.

    7. LEGAL REQUIREMENTS

    Because we do not retain Customer Content for requests covered by ZDR, we generally cannot produce it later, including for support or legal process. If applicable law or a binding legal order requires us to preserve or disclose Customer Content, we may retain it for the affected requests to the extent required and will notify you where legally permitted.

    8. NO ADDITIONAL RIGHTS

    This ZDR Policy describes our current practices. It is subject to our Terms of Service, including their disclaimers of warranties and limitations of liability, and does not create any warranty, contractual right or third-party right beyond those terms or a signed agreement with Inference.net. If this ZDR Policy conflicts with our Terms of Service or a signed agreement, such as a data processing agreement, the Terms of Service or signed agreement controls.

    9. CHANGES TO THIS ZDR POLICY

    We may update this ZDR Policy from time to time. When we do, we will revise the "Last Modified" date below and, for material changes, notify customers through the email address on their Inference.net account or a prominent notice on our website. Changes apply to requests received after the updated policy takes effect.

    10. CONTACT US

    If you have questions about this ZDR Policy, please email help@inference.net.

    Last Modified: 10/14/2026