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 text model from Google with a 65,536 token context. It accepts not only text but also images and documents, making it suitable for analyzing materials, working with code, analytics, and long, detailed responses. Batch processing is supported — tasks can be sent in batches.

Up to 32,000 tokens in a single response — this is enough for a large document, a detailed analysis, or an entire large code snippet. If the material is larger, split it into parts: the 65,536 token context window allows you to keep previous steps in the conversation.

In our data, a separate reasoning mode for this model is not noted, so we will not promise it. However, you can always ask it to break down a task step-by-step directly in the prompt — this technique usually significantly improves answers to complex logic and calculation questions.

Function calling and strict JSON schemas are not noted in our data — this is not a denial, but an absence of a label. The easiest way to check is by sending a request via the unified OpenAI-compatible BotHub API: if the format is critical for you, you can switch to another model without rewriting the integration.

The model accepts images and documents: you can send a screenshot, diagram, scan, or file and ask it to analyze the content, explain it, or summarize it. Audio and video input is not specified in our data, and the model returns results as text — there is no image or sound generation here.

There are no separate measurements for Russian in our data, so we do not provide exact estimates. The most reliable way is to test the model on your own tasks and compare it with others in the same window. In BotHub, this is available from Russia without a VPN or foreign card, with payment in rubles.