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.

It is a text model with reasoning capabilities: it analyzes long documents, answers questions about images, writes and refactors code, and assists with debugging and STEM tasks. The context window is 1,050,000 tokens, allowing an entire repository or a voluminous report with all attachments to fit in a single request.

The single response limit is 128,000 tokens. This is enough for a large technical document, detailed code analysis, or several related sections at once without splitting the task. If you need more, ask it to continue, and the model will write the next fragment in the same context.

Yes, the model's reasoning mode is confirmed: it builds a chain of steps before answering. This is noticeable in math, logic, multi-step data analysis, and bug troubleshooting, where it is important not just to guess the answer, but to carefully arrive at it and verify it.

Yes, the model supports function calling and structured JSON output—the foundation for agents, parsers, and integrations with your services. In BotHub, it is available via a unified OpenAI-compatible API, so you can switch to another model without rewriting your integration.

The model accepts images and documents as input: you can send interface screenshots, diagrams, charts, or PDFs and discuss their content. Audio and video input is not noted in our data, so for such files, it is more convenient to select a specialized model in the same BotHub window.

The language of prompts and responses is not separately specified in our data, so we cannot make promises in advance—it is more reliable to test it with your own text. The service itself is Russian-speaking: the website and Telegram bot, payment with Russian cards in rubles based on usage, without VPN or foreign cards.