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.

recraft-v4-pro-vector generates vector graphics from text descriptions and references: logos, icons, illustrations, UI elements, and branding. Suitable for designers and teams needing scalable graphics without copyright issues. The model accepts text, images, and documents as input.

The model outputs vector graphics: the image is composed of curves and fills, so it scales to any size without losing sharpness and can be easily edited in a vector editor. The quality of the result depends on how detailed your description of the object, style, and composition is.

Our data does not indicate reasoning capabilities, and it is not essential for graphic tasks: recraft-v4-pro-vector converts your description into an image. The best way to control the result is to specify the object, style, composition, and colors in the prompt.

Function calling and structured JSON output are not noted in our data for this model, so it is better not to rely on it for tool-based scenarios. It connects via the unified OpenAI-compatible BotHub API, so you can switch to another model if needed without rewriting the integration.

The model accepts images and documents: you can provide a reference to get a vector variation or base it on a brief from a file. Audio and video are not supported as input formats — BotHub has separate models for such tasks available in the same window.

We have no confirmed data on prompt language support, so it is safer to test it with your task: formulate a description, check the result, and refine details if necessary. The BotHub service itself works in Russian, with access without VPN or foreign cards, and payment via Russian cards.