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 with a 65,536 token context: it accepts text, images, and documents, reasons before answering, and can call functions. It is suitable for analyzing files and screenshots, analytics, coding tasks, and scenarios requiring a strictly structured response.

Up to 32,000 tokens per response — that's dozens of pages of text. Enough for a detailed document analysis, a long instruction, or a large code snippet. The total window is 65,536 tokens, which includes both your request and the model's response.

Yes, reasoning before answering is confirmed in our data. The model breaks down the task step-by-step before providing a result — this is especially noticeable in logic, calculations, and multi-step instructions. For simple requests, the difference is smaller, but the response is more stable.

Yes, both function calling and structured JSON output are supported. You describe the schema and available tools, and the model returns a ready-made object or a call to your function. In BotHub, this works via a unified OpenAI-compatible API, so you can switch models without rewriting your integration.

Images and documents — yes, they can be sent along with text: screenshots, diagrams, tables, PDFs. Audio and video are not noted in our data, so we won't promise them in advance — check with your own example. The model responds with text.

The language of prompts and responses is not specified in our data, so we won't promise specifics — run a couple of your typical requests and evaluate the result yourself. The BotHub interface is in Russian, payment is in rubles with Russian cards, and access is available without a VPN or foreign card.