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 model from google-gemini that accepts not only text but also images and documents as input, and responds with text. It is suitable for parsing PDFs and scans, analyzing screenshots, writing and refactoring code, and working with long materials: the context window is 65,536 tokens.

In a single response, the model outputs up to 32,000 tokens — that's dozens of pages. It's enough for a voluminous technical document, a detailed file analysis, or a large code fragment. If there is more material, break the task into parts and continue in the same dialogue; the 65,536-token context allows for this.

Our data does not indicate reasoning before answering, so we do not promise a separate reasoning mode. However, this does not mean the model cannot handle multi-step logic: ask it to write out the solution step-by-step and compare the result with other models directly in the BotHub interface.

Function calling and structured JSON output are not noted in our data, so you shouldn't rely on them in production without testing. Access is via the unified OpenAI-compatible BotHub API: test your schema, and if necessary, switch to another model without rewriting the integration.

Images and documents — yes: send a screenshot, photo, PDF, or scan and ask it to analyze the content. There are no notes in our data regarding audio and video input. The model responds with text; image and sound generation are not claimed — BotHub has separate models for that.

We do not have specific data on the quality of Russian, so we do not make an assessment. The most honest way is to test it with your task: send a request to BotHub, view the response, and if desired, compare it with another model in the same window; switching takes seconds.