Ship a Full-Stack App with One Prompt

Copy this prompt into your AI coding agent, or open it in one below.

Give this to your AI Create a to-do list app using Puter.js

Coding manually? see the guide

Recraft

Recraft API

Access Recraft instantly with Puter.js, and add AI to any app in a few lines of code without backend or API keys.

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.txt2img("A beautiful sunset", {
    model: "recraft-ai/recraft-v3"
}).then(imageElement => {
    document.body.appendChild(imageElement);
});
<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.txt2img("A beautiful sunset", {
            model: "recraft-ai/recraft-v3"
        }).then(imageElement => {
            document.body.appendChild(imageElement);
        });
    </script>
</body>
</html>

List of Recraft Models

Image

Recraft V3

recraft-ai/recraft-v3

Recraft V3 is a text-to-image model from Recraft, a design-focused AI company founded by Anna Veronika Dorogush, the creator of the CatBoost machine learning library. It's built around accurate text rendering inside generated images, an area where most image models of its era struggled beyond a few legible characters. It also supports brand style customization through reference images and control over the position and size of text elements within a design. At launch in late 2024, Recraft V3 took first place on the Artificial Analysis Text-to-Image Leaderboard hosted on Hugging Face, with an ELO score of 1172, ahead of FLUX 1.1 Pro (1143) and Midjourney v6.1 (1093), and held that position for several months. This is the raster output tier; a separate SVG variant of the same model generates vector graphics directly. It suits general-purpose image generation, marketing visuals, and product imagery.

Image

Recraft V3 SVG

recraft-ai/recraft-v3-svg

Recraft V3 SVG is the vector-output variant of Recraft's third-generation model, generating scalable vector graphics (SVG) directly from a text prompt instead of a raster bitmap. It inherits the same design-oriented training as the raster version, including accurate text rendering and brand style customization via reference images. Output is native SVG made of paths and shapes rather than a bitmap that's traced afterward, so it stays sharp at any size and opens directly in vector tools like Illustrator or Figma. Recraft is one of the few widely available text-to-image APIs that outputs vector art directly rather than rasterizing and then tracing it, part of why the underlying V3 model reached the top of the Artificial Analysis Text-to-Image Leaderboard on Hugging Face in late 2024. This tier suits logos, icons, and other vector illustration work where a scalable, editable file matters more than photographic detail.

Image

Recraft V4 Pro

recraft-ai/recraft-v4-pro

Recraft V4 Pro is the high-end raster tier of Recraft's fourth-generation image model, released in February 2026 as a follow-up to V3. Recraft describes V4 as built around design taste, tuned on composition, lighting, color relationships, and material realism rather than generic photorealism. Compared to V3, Recraft reports improved faces and anatomy, more reliable proportions and expressions, and sharper text rendering for uses like signage and packaging. The Pro tier generates at higher resolution, up to 2048x2048 pixels, aimed at print, product, and marketing work where detail needs to hold up under close inspection. The standard (non-Pro) V4 tier generates faster at lower resolution for social and web use; both tiers share the same underlying aesthetic model, differing mainly in resolution and fidelity. It suits production image generation for professional and commercial output.

Image

Recraft V4 Pro SVG

recraft-ai/recraft-v4-pro-svg

Recraft V4 Pro SVG is the vector-output counterpart to Recraft V4 Pro, generating native SVG files rather than raster images. It carries V4's design-tuned aesthetics (composition, lighting, color, and typography) into vector output, and Recraft describes it as producing finer paths and more geometric precision than the standard (non-Pro) V4 SVG tier. Output is real, editable vector graphics with structured layers, not a rasterized image converted afterward, so files open directly in tools like Illustrator, Figma, or Sketch. Native vector generation, across both the V3 and V4 generations, is one of Recraft's distinguishing features; few widely available text-to-image APIs output SVG directly at all. This tier fits large-scale brand assets, signage, detailed print illustration, and icon or design-system work where a clean, scalable vector file is the deliverable rather than a bitmap.

Image

Recraft V4 Styles Pro SVG

recraft-ai/recraft-v4-styles-pro-svg

Recraft V4 Styles Pro SVG is a variant of Recraft V4 Pro SVG built around reusable, reference-driven visual styles rather than one-off generation. Instead of choosing from a fixed preset list, it lets you attach one to ten reference images to a generation call; the model builds an internal representation of the style shared across them and returns a style ID that can be reused on later calls to keep new outputs visually consistent with that look. Recraft calls this capability Recraft V4 Styles. Output is native SVG, at the same Pro-tier fidelity as V4 Pro SVG, so paths stay clean and editable. It's priced lower than the plain V4 Pro SVG tier, reflecting a narrower, style-consistency-focused workflow rather than open-ended generation. It suits teams producing a set of icons, illustrations, or brand assets that need to share one look defined from reference art.

Image

Recraft V4 SVG

recraft-ai/recraft-v4-svg

Recraft V4 SVG is the standard (non-Pro) vector tier of Recraft's fourth-generation model, generating native SVG output from a text prompt. It shares V4's design-tuned aesthetic, including composition, lighting, color, and text legibility, with the Pro SVG tier, but Recraft describes it as standard resolution, without the finer path detail and geometric precision of the Pro version. As with the rest of the V4 SVG line, output is real vector data (paths and layers), not a raster image traced afterward, so it opens directly in Illustrator, Figma, or similar tools. It's positioned as the everyday vector tier, for brand assets like logos and wordmarks, web and print illustration, icon sets, and social graphics where scalability matters but the extra resolution of the Pro tier isn't needed.

Image

Recraft V4.1

recraft-ai/recraft-v4.1

Recraft V4.1 is the standard raster tier of Recraft's V4.1 text-to-image model family, released in May 2026 as the update to V4. It generates 1K images and is aimed at everyday work and fast iteration. Recraft reports improved photorealism, better object understanding, sharper mockups, and better prompt following, so shorter prompts give stronger results. It also adds new illustration styles. Recraft's API supports style IDs, color controls, and background settings for generation. This tier is tuned for artistic and design quality. Recraft also offers a separate Utility line that trades that expressiveness for more predictable output such as flat lighting and front-facing composition, and a Pro line that generates at 2K for print and large-scale use. Recraft has not published benchmark scores for V4.1. It suits developers who need design-oriented image generation at low cost per image.

Image

Recraft V4.1 Pro

recraft-ai/recraft-v4.1-pro

Recraft V4.1 Pro is the high-resolution raster tier of Recraft's V4.1 image generation model, released in May 2026. It accepts text and image inputs and returns images at about 2K resolution across multiple aspect ratios, double the resolution of the standard V4.1 tier. Recraft positions it for work where output quality matters most, such as brand assets, editorial illustration, and design prototyping. Compared to V4 Pro, it is described as having more natural photorealism, smoother 3D rendering and gradients, and stronger adherence to short prompts. A typical generation takes around 30 seconds. Through the API it supports image-to-image editing with a strength setting that controls how far the output departs from the source image, plus an rgb_colors palette and a background color option for keeping results on brand. It suits developers who need consistent, higher-detail raster output for production use.

Image

Recraft V4.1 Pro SVG

recraft-ai/recraft-v4.1-pro-svg

Recraft V4.1 Pro SVG is the detailed vector tier of Recraft's V4.1 image model, which generates native SVG files from a text prompt instead of raster images. It is built for complex illustrations, large-format work, and designs that need finer paths and more geometric precision than the standard V4.1 SVG model. Output is real vector data with structured layers and clean geometry, so files open directly in Illustrator, Figma, or Sketch, and scale to any size without quality loss. Prompts can be up to 10,000 characters, and it supports common aspect ratios such as 1:1, 4:3, 3:2, 16:9, and 9:16. Images generated through Replicate can be used commercially. It suits developers and designers who need a scalable vector file as the deliverable, such as brand assets, icons, detailed illustrations, and print graphics.

Image

Recraft V4.1 SVG

recraft-ai/recraft-v4.1-svg

Recraft V4.1 SVG is the standard-resolution vector model in Recraft's V4.1 line, released on May 14, 2026 as an update to V4. It generates native SVG files from a text prompt, with real paths and structured layers rather than a raster image traced afterward. Recraft lists V4.1 changes as better handling of people and facial expressions, improved natural backgrounds, better results from short prompts, smoother gradients, and more precise vector and typography output. Prompts can be up to 10,000 characters, and the API accepts several aspect ratios, including 1:1, 4:3, 3:2, 16:9 and 9:16. The output opens directly in Illustrator, Figma or Sketch and scales to any size. A higher-resolution Recraft V4.1 Pro SVG tier is available separately. It suits developers generating logos, wordmarks, icon sets, and web or print illustrations through an API when a scalable, editable file is needed.

Image

Recraft V4.1 Utility

recraft-ai/recraft-v4.1-utility

Recraft V4.1 Utility is a text-to-image model from Recraft, part of the V4.1 generation released in May 2026. It is the lighter, higher-throughput tier of V4.1, with lower cost and latency per image. Recraft says the Utility line trades the expressiveness of the main V4.1 models for predictability. Outputs use flat lighting, front-facing composition, and simple scenes. Recraft recommends it for mockups, product packshots, e-commerce listing images, and reference assets where consistency matters more than artistic variation. It keeps the prompt understanding and design sense of V4.1 at standard resolution. Recraft positions the main V4.1 models for peak quality, creative work, and final assets, and Utility for batch processing and high-volume pipelines. This tier suits developers generating many product or catalog images through an API at a predictable cost per image.

Image

Recraft V4.1 Utility Pro

recraft-ai/recraft-v4.1-utility-pro

Recraft V4.1 Utility Pro is a raster image generation model from Recraft, the higher-resolution tier of the V4.1 Utility line, released in May 2026. The Utility models are tuned for restraint rather than expressive style. Recraft describes the look as flat lighting, front-facing composition, and simple, controlled scenes. The Pro tier generates at about 2K resolution, double that of V4.1 Utility, and a typical generation takes around 10 seconds. It accepts text and image inputs, and supports options such as image strength, an RGB color palette, and a background color. It suits product imagery, e-commerce mockups, and structured visuals where output quality matters and the more stylized V4.1 Pro line would be too expressive. It is meant for developers who want predictable, clean images from an API call.

Frequently Asked Questions

What is this Recraft API about?

The Recraft API gives you access to models for AI image generation. Through Puter.js, you can start using Recraft models instantly with zero setup or configuration.

Which Recraft models can I use?

Puter.js supports a variety of Recraft models, including Recraft V3, Recraft V3 SVG, Recraft V4 Pro, and more. Find all AI models supported by Puter.js in the AI model list.

How much does it cost?

With the User-Pays model, users cover their own AI costs through their Puter account. This means you can build apps without worrying about infrastructure expenses.

What is Puter.js?

Puter.js is a JavaScript library that provides access to AI, storage, and other cloud services directly from a single API. It handles authentication, infrastructure, and scaling so you can focus on building your app.

Does this work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Recraft API through Puter.js works with any JavaScript framework, Node.js, or plain HTML. Just include the library and start building. See the documentation for more details.