# Sherpa AI Server Licenses Sherpa AI Server is a powerful tool that enables companies to implement artificial intelligence and automation on their local servers. ### Access Management and Licensing User access to Sherpa AI Server is achieved through license activation, which allows for managing access and performance. A license for one server accounts for the specified performance, measured in tokens per second. This approach gives the User the ability to adapt their solutions according to changing business needs. The platform supports [operation on both CPUs and GPUs](#user-content-fn-1)[^1], allowing customization for various computational tasks. Sherpa AI Server is compatible with several operating systems, including Linux, Windows, and macOS. This enables the integration of the platform into existing IT infrastructure and its use in various environments. The platform supports over 500 different models, giving Users the ability to find optimal solutions for their tasks. Among the supported models are language algorithms such as GPT-J, DeepSeek, LLAMA, MPT, and Mistral, as well as proprietary developments Sherpa 7B and Sherpa 13B, which are trained to solve specific tasks and support the Russian language. Sherpa AI Server provides access via an API that is compatible with OpenAI, significantly easing integration into existing applications. There is also the capability to work with Sherpa RPA, supporting the application of language models in task automation. The platform offers three types of authentication: local, LDAP, and OpenID for enhanced security. ### License Activation Process The license activation process is intuitive and accessible to every User. Authorization occurs on a special page designed for logging into the system. For this, Users need to enter the username and password of their Account, or the username and password used to create the Account within the system. ### License Options Sherpa AI Server offers several license options[^2], allowing you to choose the optimal solution based on your data processing needs: 1. Sherpa AI Server (up to 500 tokens/second) * Duration: 1 year 2. Sherpa AI Server (up to 1000 tokens/second) * Duration: 1 year 3. Sherpa AI Server (up to 2000 tokens/second) * Duration: 1 year Detailed information on creating and editing previously created licenses can be found [here](https://docs.sherparpa.ru/sherpa-ai-server/rabota-v-sherpa-ai-server/licenzii). Users can choose the most suitable option based on the expected load and the volume of data that will be processed over the year. The platform offers several levels of technical support, including online chat and email. Initially, a free trial period is available during which users can receive prompt assistance via Telegram. The Sherpa team supports clients at all stages—from model selection to the development and implementation of comprehensive AI solutions. Sherpa AI Server is regularly updated, ensuring that Users have access to the latest features and capabilities of the platform. Updates are based on User feedback and new market requirements. [^1]: For proper operation, installed components are required: Docker 18+. It is recommended to install using a Docker container; however, installation without a Docker container directly on the operating system is also possible. It can be used on a virtual server or VPS based on virtualization tools that support Docker. [^2]: For clarification on the minimum version of a specific distribution, please contact technical support. --- # Agent Instructions: 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: ``` GET https://docs.sherparpa.ru/en/licenzii/dopolnitelno/licenzii-sherpa-ai-server.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.