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 Google's universal model for working with text, documents, and images: code analysis and debugging, reasoning and STEM tasks, and file analysis. A context window of up to 1,048,576 tokens allows you to upload an entire codebase, report, or contract and get a summary, verification, or a ready-made code snippet.

Up to 32,000 output tokens in a single response — enough for a long article, technical documentation, or a large code module. If you need more, ask it to continue: the 1,048,576 token context allows you to keep the entire conversation and source files close at hand.

Yes, according to our data, the model supports reasoning and chain-of-thought before answering. This helps with tasks where step-by-step analysis is more important than a quick response: mathematics, logic, architecture design, and debugging code.

Yes, the model can call functions and provide structured output in JSON. Through the unified OpenAI-compatible BotHub API, you can connect it to your agent or service, and switch to another model if needed without rewriting the integration.

According to our data, images and documents are confirmed for input, including native file processing: diagrams, screenshots, tables, and PDFs. We have no notes regarding audio and video, so rely on text, images, and documents — these are verified scenarios.

The Gemini family of models is known for being multilingual, so the model usually handles Russian-language queries confidently. We don't have exact specifications in our data, so test it with your own tasks: access from the Russian Federation is open without a VPN or foreign card, and payment is in rubles.