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 text model: it accepts text, documents, and images as input and responds with text. It is suitable for analyzing long materials, research tasks, preparing reports, working with code, and summarizing PDFs or screenshots. The context is 65,536 tokens, which is enough for voluminous collections.

The output limit is 32,000 tokens per response. This is sufficient for a detailed report, a long article, or a large code file in its entirety, without splitting it into parts. If the material still doesn't fit, ask it to continue — the model will write the next fragment in the same dialogue.

A separate reasoning mode is not noted in our data, but that doesn't mean it doesn't exist. In practice, a simple trick helps: ask the model to break down the task step-by-step and show its logic before outputting — for complex questions, the quality of answers noticeably improves.

Function calling and strict JSON output are not marked in our data, so we cannot guarantee them. However, you can specify the response format in the prompt: describe the required structure and an example, then test the result with your scenario. Access is provided via the unified OpenAI-compatible BotHub API.

Images and documents — yes: upload a screenshot, diagram, scan, or PDF, and the model will analyze the content and respond with text. Audio and video as input formats are not noted in our data, so you shouldn't count on them; it's better to convert the audio track to text beforehand.

The model's data does not describe supported languages, so we won't promise anything specific — it's easier to test it with your own text and documents. The BotHub interface is in Russian, access works from Russia without a VPN or foreign card, and payment is accepted with Russian cards in rubles.