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 code-focused model: writing functions, refactoring, analyzing third-party repositories, debugging, and explaining logic. A 400,000-token context allows you to keep large files, documentation, and entire technical specifications in the dialogue without cutting them into pieces.

Up to 128,000 tokens per response—enough for a large code module, extensive documentation, or a detailed project analysis. If the task is larger, simply continue the dialogue: in BotHub, you pay for tokens as you use them, without a subscription, and the balance does not expire.

Yes, the reasoning mode is confirmed: before the final answer, the model works through the task step-by-step. This is noticeable in debugging, architectural design, and STEM tasks, where it is important not to guess the result, but to consistently break down the conditions and verify intermediate conclusions.

Yes, both function calling and structured JSON output are supported. The model is easy to integrate into agents and pipelines: it selects the necessary tool and returns a predictable structure. In BotHub, this is available via a unified OpenAI-compatible API, so switching models does not break the integration.

Images and documents—yes: send a screenshot of an error, an interface diagram, or a PDF with specifications, and the model will analyze the content. We have no data on audio and video, so it is more convenient to choose a specialized model for such files in the same window.

There are no separate measurements for Russian in our data, so we won't make promises—it's more reliable to test it on your real task. The service itself is fully Russian-language: access from Russia without a VPN or foreign card, payment with Russian cards, and tokens do not expire.