> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/docs/en-us/about/privacypolicy.md). # Privacy Policy ## Cherry Studio Privacy Policy Updated: August 20, 2026 Effective Date: August 20, 2026 Welcome to Cherry Studio (hereinafter referred to as "this software" or "we"). We place great importance on your privacy protection. This Privacy Policy explains how we handle and protect your personal information and data. Please read and understand this Policy carefully before using this software. ### I. Scope of Information We Collect To ensure the normal operation of the software, optimize user experience, and improve product quality, we will collect the following fully anonymized non-personal operational information by category. All information is anonymized, does not contain any data that can identify you personally, and cannot be linked to your personal information. You always retain full control over all information collection activities; specific methods are described below. #### (1) Basic Operational Information This type of information is used to ensure the normal operation, security, and version compatibility of the software’s basic functions. The default collection scope is as follows: * Software version information: used for version compatibility checks, security update notifications, etc.; * Aggregated functional usage information: overall usage summary of each function (without involving details of specific usage behavior). #### (2) Product Improvement Information To continuously improve the product experience, we will collect the following information by default: * Functional activity and frequency of use: the level of activity and frequency with which each function is used; * Error logs and crash information: anonymized error logs, crash stack information, etc. generated during software operation, used for troubleshooting and improving stability. The above information is highly aggregated anonymous data and does not involve your conversation content, API Key, or any personal identity information. **How to disable:** You may disable the collection of the above two categories of information at any time via the corresponding switches under \[Settings] - \[Data Settings] - \[Privacy Settings]. Disabling them will not affect the normal use of the software’s core functions. If you disable the collection of basic operational information, you may not receive version compatibility prompts and security update notifications in a timely manner. #### (3) Our Commitment Whether it is basic operational information or product improvement information, we promise: * All data is anonymized and cannot be linked to your personal identity; * It will not be used for user profiling or ad targeting, nor will it be sold or otherwise provided to third parties (except where required by laws and regulations); * It will not include any sensitive data such as your conversation content, API Key, or knowledge base content (see Article 2). ### II. Information We Explicitly Do Not Collect To protect your privacy and information security to the greatest extent, we explicitly promise that we will not collect, store, transmit, or process the following data: * **Your API Key:** The model service API Key information you enter into this software; * **Your conversation data:** Any conversation data generated during your use of this software, including but not limited to chat content, instruction information, knowledge base information, vector data, and other custom content (except for the immediate relay necessary to complete inference when using the built-in model service described in Article 4; we will not record or store the relevant content); * **Personal identity information and sensitive personal information:** Any information that can directly or indirectly identify your personal identity, as well as sensitive personal information as defined by laws and regulations. ### III. Local Storage and Data Exchange Description **Local data storage:** Your API Key, chat history, and personal preference settings are stored by default on your local device. Cherry Studio does not provide cloud synchronization services and will not upload this data to our servers (except for the immediate relay necessary to complete inference when using the built-in model service described in Article 4). **Direct connection:** When you use a third-party model service that you have configured yourself, this software, as a local tool, provides interface-calling functions to the third-party model service. Your terminal device will establish a network connection directly with the server of the third-party model provider you configured (such as OpenAI, Anthropic, etc.), and the relevant data will not be relayed through our servers. **Content compliance obligations:** Whether you use the built-in model service described in Article 4 or a third-party model service configured by yourself, you must not use this software to create, copy, publish, distribute, or spread any illegal or harmful information that violates the laws and regulations of the People’s Republic of China or the applicable laws and regulations of your country/region, endangers national security, harms national honor and interests, undermines ethnic unity, spreads rumors, disrupts social order, promotes obscenity or pornography, violence, or infringes the lawful rights and interests of others. ### IV. Built-in Model Service Cherry Studio provides a built-in model service that does not require you to configure an API Key yourself. When using this service, the prompts, conversation context, and model responses required to complete inference are relayed through Cherry Studio’s official service. The relay service processes only the current request, does not record or store the relevant content, and discards it immediately after the request is completed. It will not be used for any purpose other than the current request. The upstream model service provider corresponding to the built-in model service will process such request content within the scope of its services, subject to its privacy policy. The built-in model and its service provider may change based on service conditions. You may also choose to use other model services that you configure yourself. The built-in model service depends on the capabilities of upstream model service providers and may be interrupted, delayed, or unavailable due to service adjustments, network conditions, or upstream changes. Model output is automatically generated by the model. We do not guarantee its accuracy, completeness, or applicability, and you should make your own judgment and bear the risks of using such content. To the extent permitted by law, we are not liable for losses arising from the use of the built-in model service. ### V. Privacy Policy Statement of Third-Party Model Service Providers When you use the API Key of a third-party model service provider that you have applied for and configured yourself to conduct AI conversations, you are in fact directly accepting the services of that third-party model service provider: You shall bear the privacy and compliance risks involved in using third-party model service providers. Each model provider (such as large model vendors) will process the data you actively input (such as conversation content) according to its own privacy policy, data security measures, etc., and may independently collect other related data within its service scope. The above processing and collection activities are not controlled by this software, and the switches in this software’s \[Privacy Settings] cannot disable such activities. If you want to learn about or disable the relevant data processing and collection activities, please refer to the privacy policy on the official website of the selected model service provider and seek its instructions for disabling them. We assume no responsibility for this. ### VI. Special Notes on Third-Party Services To facilitate your management and processing of data, in \[Settings] - \[Data Settings] of this software, we support third-party service functions including but not limited to the following, which you may choose to configure and use yourself by entering the API address, username, password, etc.: * **Cloud backup settings:** WebDAV, S3-compatible storage, Nutstore; * **Third-party integrations:** Notion, Yuque, Joplin, Obsidian, SiYuan Note, etc. The specific third-party services supported are subject to what is actually displayed in the client. When you use the above third-party services through this software: API Keys, passwords, and other credentials you enter are used only locally on your device. This software will not collect or store such information or data. Please keep your credentials properly secured yourself. The third-party services are independently operated by their respective providers, and their data processing activities (including collection, use, storage, and sharing) are governed by the providers’ own privacy policies and terms. We recommend that you carefully read and understand the relevant providers’ privacy policies and terms of service before connecting, use the third-party services in compliance, and bear all risks and responsibilities arising from your use of the corresponding services. We assume no responsibility for data breaches, loss, or improper processing resulting from your use of third-party services. At the same time, please be aware that the above third-party service providers may independently collect your data within their service scope, and such collection is not controlled by this software. The switches in this software’s \[Privacy Settings] cannot disable such collection either. If you need to disable it, please seek the method from the relevant third-party service provider. ### VII. Disclaimer for Third-Party Service Providers and Third-Party Services #### (1) Independence of Third-Party Services This software is open-source software and can help users connect to, configure, and use artificial intelligence models, APIs, web services, and other related services provided by third parties (hereinafter collectively referred to as "Third-Party Services"). Unless otherwise expressly stated by this software, all third-party services are independently provided, operated, and borne by the corresponding third-party service providers. The provision of connection and configuration functions by this software does not create any agency, joint operation, co-operation, guarantee, authorization to charge, or other similar legal relationship between this software and the third-party service providers. A user’s configuration or use of third-party services through this software does not mean that this software is the provider, seller, charging party, or settlement party of such third-party services. This article applies to third-party services configured and used by users themselves and does not apply to the built-in model service described in Article 4. #### (2) Fees and Billing for Third-Party Services Whether third-party services are charged, their pricing standards, free quotas, model prices, Token prices, cache prices, multipliers, packages, top-up discounts, currency conversion methods, settlement rules, and other billing policies shall all be subject to the rules actually announced and implemented by the corresponding third-party service providers. This software does not participate in the actual billing, deduction, top-up, refund, or settlement process of third-party service providers, and cannot guarantee the real-time acquisition of the latest, complete, and accurate billing information from all third-party service providers. Fees incurred by users from using third-party services shall be settled directly between the user and the corresponding third-party service provider in accordance with its service agreement, pricing policy, and actual usage. #### (3) Client-Side Pricing and Related Information To improve the user experience, this software may display model prices, free status, Token unit prices, context length, model names, model capabilities, or other information related to third-party services in the client. The above information is for reference only and does not constitute a quotation, billing commitment, free-of-charge commitment, price guarantee, or other contractual commitment made by this software or the third-party service provider to users, nor should it be used as the sole basis for determining the final amount charged by the third-party service. This paragraph does not apply only when this software explicitly states that the information is provided in real time by the relevant service provider and serves as the official basis for billing. Because third-party service providers may adjust prices, models, free policies, multipliers, billing methods, or other service rules at any time, the information displayed in this software may be delayed, omitted, incorrect, invalid, or inconsistent with the actual rules of the third-party service provider. Before using third-party services that may incur charges, users should verify the latest prices and billing rules through the official channels provided by the corresponding third-party service provider. #### (4) API Key and Account Responsibility When a user independently provides, configures, or authorizes the use of a third-party service API Key, access token, account, or other authentication information, they should first verify the balance, permissions, free quota, billing rules, and security status of the corresponding account. Call charges, excess charges, balance deductions, or other economic losses arising from the user’s configuration, use, or management of third-party accounts, API Keys, or third-party services shall be handled by the user and the corresponding third-party service provider in accordance with its rules. #### (5) Third-Party Service Exceptions and Disputes Service interruptions, model changes, price adjustments, billing anomalies, duplicate charges, account freezes, insufficient quota, refund disputes, API errors, data loss, service unavailability, or other issues caused by third-party service providers shall be claimed or resolved directly by the user with the corresponding third-party service provider. Within a reasonable scope, this software may provide the user with necessary technical information or assistance in troubleshooting based on the actual situation, but such assistance does not mean that this software assumes responsibility for the third-party service, nor does it constitute a guarantee or endorsement of the third-party service provider’s behavior. Charges, deductions, refunds, and service actions independently implemented by third-party service providers do not become actions or liabilities of this software merely because the user uses the third-party service through this software. ### VIII. Policy Updates and Revisions This Policy may be updated from time to time. When this Policy undergoes material changes (including but not limited to changes in the scope of information collection, changes in user rights, or changes in data processing methods), we will inform you in advance through prominent in-app notices, version update notes, etc., and clearly mark the update date and effective date in the new version. Please review it promptly. If you continue to use this software after this Policy takes effect, you will be deemed to have understood and accepted the updated Policy content. ### IX. Contact Us If you have any questions about this Policy or Cherry Studio’s privacy protection measures, or if you need to communicate with us regarding the processing of your information, please feel free to contact us through the following means: **Contact email:** We will respond within 15 working days after receiving your request. Thank you for choosing and trusting Cherry Studio. We will continue to provide you with a safe and reliable product experience. Updated: August 20, 2026 --- # 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.cherryai.com.cn/docs/en-us/about/privacypolicy.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.