You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.

This is a Google Gemini family model with a 65,536 token context. It works with text, analyzes documents and images, reasons before answering, calls functions, and can output results via voice. It is suitable for file analysis, coding, conversational scenarios, and voice assistants.

You get text and audio as output: the model can voice the answer, not just print it. The limit for a single response is 32,000 tokens, which is enough for a long analysis, article, or detailed breakdown of the solution logic.

Yes, reasoning before answering is confirmed by our data. The model first builds a solution path and only then provides the result — this is noticeable in tasks involving logic, mathematics, multi-step instructions, and analyzing conflicting requirements in a document.

Yes, both are supported. You describe the functions, the model decides when to call them, and returns the answer in the specified JSON schema. This is convenient for agents and integrations: on BotHub, the model is available via a unified OpenAI-compatible API.

According to our data, images and documents are accepted as input: you can send a screenshot, diagram, PDF, or contract and ask to analyze the content. Audio and video input is not specifically noted in our data, so it is better to test this scenario with your own task.

The language of prompts and responses is not described in our data, so we will not promise specific Russian quality — please check with your own task. BotHub itself is Russian-speaking: the interface, payment by Russian cards in rubles, and access without VPN, and the model can be changed in the same window if necessary.