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 from the Gemini 2.5 Flash Lite line. It accepts text, images, and documents, can reason before answering, call functions, and output structured JSON. It is suitable for large volumes of repetitive tasks: document parsing, data extraction, chats and support, and draft code work.

Up to 32,000 tokens per response — this is approximately several dozen pages of text. If you need more, ask it to continue in parts. The model's input window is 1,048,576 tokens, so long source files and document collections can be sent in their entirety.

Yes, the reasoning mode is confirmed in our data. The model breaks down the task into steps internally and only then provides the result — this significantly helps with logic, calculations, and parsing complex conditions. In the API, reasoning depth is controlled by request parameters.

Yes, both. The model calls external functions and tools, and can output responses strictly according to a specified JSON schema — convenient for parsers and pipelines. In BotHub, this works via a unified OpenAI-compatible API, so you won't need to rewrite your integration.

Images and documents — yes: send a scan, PDF, or picture and ask it to parse the content, extract tables, or describe a diagram. Audio and video input is not noted in our data, so for such files, it is more convenient to choose a specialized model from the catalog.

The quality of Russian language processing is not documented in our data, so we won't make any promises — it's better to test it with your own scenario: run a couple of typical queries and compare it with another model in the same window. Access without VPN or foreign cards, payment in rubles based on actual token usage.