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 from the Gemini Robotics-ER line: it is designed for spatial scene understanding based on images and text descriptions. It accepts text, images, and documents, and responds with text. It is suitable for robotics prototypes, frame analysis, and visual scenarios where objects and their positioning are important.

The output limit is 32,000 tokens per response, which is enough for a long analysis or a detailed instruction. The total context window is 65,536 tokens, which includes your request with attachments and the response itself, so it is better to request very voluminous texts in parts.

There is no indication of a reasoning mode in our data, but we do not claim the opposite either. In practice, the prompt determines a lot: ask it to break down the task step-by-step, show intermediate conclusions, and only then provide the result — the model handles this response structure well.

There is no specific note about function calling and strict JSON in our data, so we cannot provide guarantees — please test it in your scenario. The output format can be set directly in the prompt: describe the required schema and ask for the response only in that structure. Access is provided via the unified OpenAI-compatible BotHub API.

Images and documents — yes, this is confirmed by our data: attach frames, diagrams, scans, and ask it to analyze the content. We have no notes regarding audio and video, so you should not count on them; for sound and video streams, BotHub has separate models, with one-touch switching.

There is no information about supported languages in our data, so we will not promise anything specific — it is fairer to test the model on your task. On the BotHub side, everything is familiar: a Russian-language website and Telegram bot interface, payment with Russian cards in rubles, without VPN or a foreign card.