> 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/model-settings.md). # Model Settings ## Model Name and Cover Image On the Model Settings page, you'll have the opportunity to modify the model name and the cover image. Feel free to set them up so that the Model will be easy to find among all your other Models. ## Model ID Every model has a unique ID which is generated at creation time. {% hint style="info" %} Model Templates in the Catalog do not have a Model ID. The Model ID is generated when the Model is created from the Template. If two users create a Model from the same Template, each Model gets its own unique Model ID. {% endhint %} You will need the Model ID in order to [use the Mindee API](/integrations/api-overview.md). In the Model Settings page, you can view and copy the Model ID. The Mindee Support team may request the Model ID to diagnose issues and provide solutions. ## 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 ## Copy the Model It can be useful to copy an existing model for some types of workflows. You can have a base "template" model that is not called directly, but is used to make derivative models. This way you can have a common base and then modify the Data Schema to account for different providers, geographies, downstream users, etc. Each of these derivative models would be a copy of the "template" model. You can also us this as way for testing changes to a model. For example you can copy a model used in production, modify the copy, and test the modifications in staging. Once the modifications are tested successfully, switch production over to the new model. ## Lock the Model To prevent unintended changes once your model configuration is finalized, you have the option to lock the model. This will prevent all changes to the model's Data Schema and Optional Features. This is useful for ensuring that the model remains stable for production use. {% hint style="warning" %} Locking the Model is an **irreversible action**, you will not be able to unlock it afterwards. **Note**: you can copy a locked model and modify the copy. {% endhint %} ## Delete the Model You can delete a model at any time. {% hint style="danger" %} Deleting a model is an **irreversible action**, all data will be lost forever! {% endhint %} Deleting a model also deletes: * Documents and results stored in the [Documents History](/models/live-test.md#documents-history) * Documents and annotations in the [RAG database](/extraction-models/optional-features/improving-accuracy.md) * All [Insights](/account-management/insights.md), including API calls --- # 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/model-settings.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.