How it works Recraft V3?
Recraft V3 is an image generation model from the Recraft team. It accepts text and images as input, outputting ~1K resolution images in various aspect ratios, with image_config parameters allowing for precise result customization. BotHub provides access to Recraft V3 without VPN or foreign cards: pay with Russian cards in rubles, only for tokens used. With over 250 models in one window, it's easy to compare results with other generators. For production tasks, we offer a unified OpenAI-compatible API and corporate access with contracts and an admin panel. Useful for designers creating concepts and layouts, marketers for banners and covers, SMM specialists for feed and story visuals, and illustrators for quickly sketching variations based on references.Frequently asked questions about Recraft V3
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 V3 generates images from text descriptions and processes existing images in image-to-image mode. It is suitable for illustrations, banners, covers, concepts, social media visuals, and presentations. It also accepts images and documents as input if you need to describe or analyze their content.
The model provides ready-made images that you can download directly in BotHub or receive via API. Specific sizes and aspect ratios are set via request parameters, so it is easiest to generate several variations of a prompt and choose the image with the best detail.
A dedicated step-by-step reasoning mode is not noted for Recraft V3 in our data: it is primarily a generative model for images. If you need a chain of thought for a complex task, switch to a text-based reasoning model in the same BotHub window.
Function calling and strict structured output are not noted for this model in our data. However, access is provided via the unified OpenAI-compatible BotHub API, so you can call Recraft V3 for images and connect another model for tools and JSON without rewriting your integration.
Yes, the model accepts images and documents as input: you can send a reference and request a variation or processing in image-to-image mode. Audio and video are not listed among supported formats; BotHub has separate specialized models for them.
We have no confirmed data on prompt language support, so our universal advice is: describe the scene with simple, short phrases, listing objects, style, angle, and lighting. The BotHub interface is in Russian, access works without VPN or foreign cards, and payment is in rubles.