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.

According to our data, the model accepts text, images, and documents, can reason before answering, and call functions. It is suitable for parsing files and screenshots, preparing and editing texts, including lines for voiceovers, as well as for scenarios where the response needs to be returned as structured JSON.

The limit for a single response is 32,000 tokens, which is dozens of pages. The total context window is 65,536 tokens, and it includes everything: your request, attached documents, and the response itself. If the material is large, break the task into parts to keep some context buffer.

Yes, reasoning before answering is confirmed by our data. The model can break down a task into steps and only then provide a result — this is noticeable when parsing documents, comparing options, and in tasks where the sequence of actions is important, rather than the first formulation that comes to mind.

Yes, function calling and structured JSON output are supported. The model can be connected to your tools to receive responses in a specified schema. In BotHub, it is available via a unified OpenAI-compatible API, so switching to another model does not require rewriting the integration.

According to our data, in addition to text, images and documents are accepted as input: you can send a screenshot, diagram, scan, or file and ask to parse the content. Support for audio and video is not noted in our data, so such formats should be tested with your specific task.

Our data does not track prompt and response languages, so we cannot make exact promises here — it is easier to test the model with your typical request. The BotHub service itself works in Russian, is available from Russia without a VPN or foreign card, and payments are processed with Russian cards.