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 model from the Gemini line that responds with text and accepts text, images, audio, and documents as input. It can reason before answering and call functions. The 1,048,576 token context is suitable for analyzing large documents, working with code, analytics, and API integrations.

The output limit is 65,536 tokens per response. This is enough for a voluminous document, a detailed analysis, or a large code module in its entirety, without splitting it into a dozen requests. If the material is larger, split the task into parts: the 1,048,576 token context will keep the entire source in the dialogue.

Yes, the model has a reasoning mode: before the final answer, it breaks down the task step-by-step. This is noticeable in logic, mathematics, STEM tasks, and code debugging, where it is important not to guess the answer, but to consistently arrive at it and verify intermediate conclusions.

Yes, the model supports both function calling and structured JSON output. You describe the schema and tools, and the output is a predictable object that goes directly into your code. In BotHub, this works via a unified OpenAI-compatible API, so you can switch models without rewriting the integration.

The model accepts images, audio, and documents as input — these are confirmed capabilities, including native document handling. There is no note about video in our data, so it is safer to test this scenario with your own file. In any case, the model returns the answer as text.

We do not have specific data on languages, so we won't make promises — it's easier to test it with your real task. In BotHub, this is not just talk: access from Russia without a VPN or foreign card, payment in rubles based on actual usage for tokens that do not expire.