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 an OpenAI model focused on code: writing functions, analyzing unfamiliar projects, refactoring modules, and finding the cause of errors. The 400,000-token context allows you to upload many files and documentation at once. It accepts images and documents, making it suitable for both error screenshots and technical specifications.

The limit for a single response is 4096 tokens, which is roughly several pages of text or a substantial code file. For large refactoring or long documentation, break the work into parts and continue in the same dialogue: the 400,000-token context is enough for the model to remember everything previous.

Yes, before answering, the model builds an internal chain of thought — this is noticeable in tasks involving logic, algorithms, and debugging. The depth of reasoning and detail of the response can be adjusted using effort and detail parameters, choosing a balance between speed and solution thoroughness. This works the same way in the BotHub chat and via API.

Yes, both function calling and structured JSON output are supported: the model decides when to call your tool and returns the response according to the specified schema. It is convenient for agents and integrations, and the unified OpenAI-compatible BotHub API allows you to switch to another model without rewriting code.

According to our data, images and documents are accepted as input: send an interface screenshot, diagram, chart, or specification file and ask it to analyze. Audio and video are not listed in the supported formats — for those, there are separate transcription and recognition models in the BotHub catalog.

The model's data does not specify languages, so we won't promise anything specific — it's easier to test it with your own task: formulate a request and compare the result with another model in the same window. The BotHub interface is in Russian, payment is via Russian cards, and no VPN or foreign cards are needed.