> For the complete documentation index, see [llms.txt](https://docs.mindee.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mindee.com/models/data-processing-policies.md). # Data Processing Policies The following features help ensure compliance with your regional regulations and allow control over data retention and privacy. ## Processing Zone The **Processing Zone** setting determines the geographic region where your document will be processed. This option can impact compliance with data residency requirements (e.g., GDPR, CCPA). The processing zone can be set for all models in the [organization settings page](https://app.mindee.com/settings?tab=organization). If you need to set the processing zone for a specific model, it can be accessed on the model's "General Settings" page. Available options: * **No Preference (Default)**\ Mindee will automatically route your documents to the closest or most available processing region. This is the recommended default for optimal performance and availability, but your data may be processed in Europe and in the United States. * **Europe**\ Forces all data processing to occur exclusively within data centers located in Europe (EU). Recommended for organizations subject to GDPR or EU data residency policies. * **United States**\ Forces all data processing to occur exclusively within data centers located in the United States. Recommended for organizations subject to U.S. data governance or compliance policies. {% hint style="info" %} This is only a zone for *processing*, not extraction or analysis support. **You can send documents from any country to the Mindee API!** {% endhint %} ## Storage Policy This section applies when sending documents via API call. The **Storage Policy** defines how long extracted data (i.e., the results of document processing) is retained in Mindee’s systems before being permanently deleted. The original uploaded file is never stored to disk. #### Storage Duration * Defines the exact number of hours that extracted data is stored. * **Default:** 12 hours * **Minimum**: 1 hour * **Maximum**: 24 hours Data is automatically deleted as soon as the storage duration expires. During this time, you may make GET requests to retrieve the payload using its inference ID. After this period, any calls to the inference ID or job ID will result in a 404 error. This setting helps balance between accessibility of results for your workflow and minimizing retention for privacy and compliance. #### Delete Extracted Data When Fetched When **disabled**, data will be retained until the configured **Storage Duration** elapses. **(Default)** When **enabled**, extracted data is automatically and permanently deleted immediately after: * the inference is accessed using a GET request (usually when polling) * the inference is successfully sent to your server via a [webhook](/integrations/webhooks.md) The data will be deleted regardless of the Storage Period setting. Once the Storage Period is passed, the data will be deleted regardless of whether this option is enabled. Once the data are deleted, any calls to the inference ID will result in a 404 error. This option is recommended for workflows where: * you only need to access the data once * you are storing the data from each API call in your system * there are operational requirements that specify a Zero Data Retention policy ## Best Practices * **For testing and setup:** Use a longer Storage Duration (up to 24 hours) to allow time to check and validate processed results. This is particularly useful when setting up a webhook workflow. * **For general production use:** Set a relatively short Storage Duration (3-5 hours). * **For privacy or Zero Data Retention:** Always enable **Delete When Fetched.** Best to also set a short Storage Duration (1 hour) in case of failed calls (i.e. network failure on GET). * **For compliance:** Select the Processing Zone that matches your legal and regulatory requirements. ### Example Configuration * **Processing Zone**: Europe * **Storage Duration**: 4 hours * **Delete When Fetched**: Enabled With this setup, all documents are processed in EU data centers, results are stored for a maximum of 4 hours, and deleted automatically once you first download them. ## **Configure the Data Processing Policy** {% hint style="warning" icon="money-check-dollar-pen" %} This feature is not available on all plans, check the [Plans](/account-management/plans.md#feature-comparison) section for more information. {% endhint %} {% @supademo/embed url="" demoId="cmevfnfze75icv9kqgqida892" %} ## Frequently Asked Questions
Is Mindee GDPR & SOC 2 Type II compliant? Yes. Mindee V2 is fully GDPR-compliant and maintains its SOC 2 Type II certification, ensuring rigorous security controls, data protection standards, and transparency for enterprise needs.
Can I request data deletion at any time? Yes. You can request full or partial data deletion at any time by using the deletion features available in your [model settings](/models/model-settings.md#delete-the-model), [organization settings](/account-management/organizations.md#delete-organization), or [account settings](/account-management/account-settings.md#delete-account). Mindee ensures that your data is securely and permanently removed upon request. You can also contact our support team if you are unsure.
--- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.mindee.com/models/data-processing-policies.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.