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 text model with a one-million token context window. It analyzes long documents and codebases, writes and refactors code, helps with debugging, answers questions about uploaded files and images, and works with function calling in your services.

In a single response, the model generates up to 32,000 tokens — enough for a long article, a detailed document analysis, or a large code file. If you need more volume, break the task into parts: the one-million token context allows you to keep the entire conversation history.

In our data, a separate reasoning mode is not noted for this model; it answers immediately, which provides high speed. However, you can ask it to write out the solution step-by-step directly in the prompt: for math, logic, and STEM tasks, this usually significantly improves the result.

Yes, function calling and structured JSON output are supported. The model connects to your tools, returns answers in a specified schema, and integrates neatly into pipelines. Through the unified OpenAI-compatible BotHub API, you can switch to another model without rewriting your integration.

In addition to text, the model accepts images and documents as input, with files processed natively without separate recognition. Audio and video are not noted in our data, so for voiceovers or analyzing recordings, it is more convenient to use a specialized model in BotHub, which opens in the same window.

The Gemini family is inherently multilingual, and in practice, the model works confidently with Russian: it answers based on documents, writes code, and explains solutions. We do not have exact data on languages, so the best way is to test it on your tasks in BotHub and compare it with other models in the same window.