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 with a 200,000 token context that accepts text, documents, and images as input. It is suitable for analyzing large reports and research, analytics, preparing reviews, and working with code — tasks where you need to keep a lot of material in mind at once.

Up to 32,000 tokens in one response — that's dozens of pages. Enough for a detailed analytical report, a large section of documentation, or a detailed document analysis. If there is more material, break the task into parts and continue in the same dialogue, relying on the long context.

Our data does not contain a specific note about reasoning before answering, so we will not promise a hidden thinking mode. In practice, it helps to ask the model to break down the task step-by-step directly in the prompt — then the train of thought is visible in the response itself.

Function calling and structured output are not marked in our data, but that does not mean they are absent. You can describe the required JSON format directly in the prompt. If tools are important to you, test the model's behavior on your scenario via the unified OpenAI-compatible BotHub API.

Images and documents — yes, they can be sent along with text: the model will analyze a screenshot, diagram, table, or multi-page file. Audio and video input are not marked in our data, so for such formats, it is more convenient to choose a specialized model in the same BotHub window.

The language of prompts and responses is not specified in our data, so we will not promise quality in advance. The most honest way is to send your real request and see the result: in BotHub, the model is available without a VPN or foreign card, with payment via Russian cards.