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 model that accepts text, documents, and images as input and outputs text. It is suitable for analyzing files and screenshots, preparing drafts and summaries, working with code and explanations, as well as batch processing large sets of requests via API.

The output limit is up to 32,000 tokens per response, which is enough for comprehensive analysis, a long article, or detailed documentation. The context window is 200,000 tokens, so you can upload a large document into the chat and get a detailed result in its entirety.

A separate reasoning mode is not noted in our data, so we will not promise it. In practice, you can ask the model in the prompt to break down the task into steps and show the logic — this often improves the quality of the answer for complex questions.

Function calling and strict structured output are not noted for this model in our data. If a JSON schema is critical for your service, specify the format directly in the prompt or switch to another model — the unified OpenAI-compatible BotHub API does not require rewriting the integration.

The model accepts images and documents: you can send a screenshot, diagram, scan, or file and ask to analyze the content. Audio and video input is not noted in our data, so for such tasks, it is better to choose a specialized model from the BotHub catalog.

We do not have confirmed data on quality for specific languages, so it is more reliable to test it with your tasks. In BotHub, this is convenient: access from Russia without a VPN or foreign card, pay-as-you-go for tokens, and quick comparison with other models in one window.