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 versatile model: it accepts text, images, and documents, reasons before answering, calls external functions, and can not only write but also voice the response — audio generation is noted in our data. It is suitable for voice assistants, dialogue scenarios, file analysis, and text-to-speech.

Our data confirms audio generation, but exact parameters — file format, sample rate, bitrate — are not specified, so we will not invent them. What is known for sure: a 200,000 token context window and up to 32,000 tokens in a single response.

Yes, the reasoning mode is confirmed by our data: before the final answer, the model builds an internal chain of steps. This helps where logic is important — document analysis, multi-step instructions, calculations, choosing the right tool. For complex queries, you will have to wait a little longer for the answer.

Yes, both function calling and structured JSON output are supported. The model decides which tool to call and returns the answer according to the specified schema — this is convenient for integrations. On BotHub, everything works via a unified OpenAI-compatible API, so there is no need to rewrite code for a different model.

Images and documents — yes, this is confirmed: send a screenshot, diagram, table, or PDF and ask to analyze the content. Input of audio and video is not noted in our data, so it is easier to check this with your own file directly in the interface.

Our data does not have an assessment by individual languages, so we will not provide specific figures. Google Gemini models were created as multilingual, but it is more reliable to check in practice: send your typical query and compare the result with another model — switching in one BotHub window takes a couple of seconds.