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.

riverflow-v2-pro by sourceful works with text and images: it accepts text, documents, and images as input, and outputs text or images. It is suitable for generating visuals from text descriptions, processing images based on references, and analyzing documents.

Specific resolutions and file formats are not specified in our data, so we cannot promise exact figures. The model creates images from text descriptions or source images; the context window is 8192 tokens, and maximum output is 7372 tokens. It is easiest to check parameters with test prompts.

A separate reasoning mode for riverflow-v2-pro is not noted in our data, but that does not mean it doesn't exist: the label is simply missing. If you need step-by-step reasoning, ask for it in the prompt or switch to a reasoning model in the same BotHub window.

Function calling and structured JSON output are not marked in our data, so we cannot guarantee them. The easiest way to check is by sending a request via the unified OpenAI-compatible BotHub API: if a strict schema is required, there are other models with confirmed tool support nearby, and you won't have to rewrite the integration.

You can upload images and documents — this is confirmed: the model reads the image and file and responds with text or creates a new image based on a reference. Audio and video inputs are not noted in our data, so for audio or video analysis, it is better to use a specialized model.

The language of prompts and responses is not described in our data, so we will not make any claims — it is fairer to test it with your own tasks. BotHub itself is fully in Russian: interface, support, payment with Russian cards in rubles, and access without VPN.