# Recraft V3

Recraft V3 builds on Recraft V2 with a major expansion in style control. It introduces 20+ specialized styles from realistic portraits to pixel art, native vector output, and improved text positioning.

- **Model ID:** `recraft/recraft-v3`
- **Type:** image
- **Providers:** recraft
- **Context window:** Not applicable
- **Maximum output tokens:** 0
- **Pricing:** $0.04/image
- **Canonical page:** https://vercel.com/ai-gateway/models/recraft-v3

## Supported parameters

- **Parameters:** Not reported
- **Operations:** `text-to-image`, `image-to-image`, `inpainting`, `outpainting`, `background-removal`, `vectorization`, `creative-upscale`
- **Input modalities:** `text`, `image`
- **Output modalities:** `image`
- **Aspect ratios:** Not reported
- **Resolutions:** Not reported
- **Durations:** Not reported
- **Frame rates:** Not reported
- **Maximum outputs per request:** Not reported
- **Maximum input images:** Not reported
- **Input image formats:** Not reported
- **Maximum input image size:** 5 MB

## Example

```ts
import { experimental_generateImage as generateImage } from 'ai';

const result = await generateImage({
  model: 'recraft/recraft-v3',
  prompt: 'A red balloon on a wooden table.'
});
```

## About

Recraft V3 is Recraft's second-generation image model. It expands the V2 foundation with improvements in style control, text generation, and anatomical accuracy.

The most visible addition is the style library: 20+ specialized presets covering realistic portraits, digital illustrations, pixel art, vector graphics, and more. These presets give you direct control over visual direction without prompt engineering workarounds. Select a preset and the model applies that aesthetic consistently.

Text generation also improved in V3. The model handles long multi-word text with precise positioning within compositions. Combined with anatomically correct output (correct proportions, natural poses, realistic hands and faces), V3 produces images that need less post-production correction.

Native vector output is another V3 addition. Generate scalable vector graphics directly for logos, icons, and print assets. No need to rasterize and trace. This fits into professional design toolchains where vector formats are the standard.

## What to consider

Recraft V3 introduced the style library that defines the Recraft design workflow. Confirm per-image rates. If your pipeline needs style presets (realistic portrait, digital illustration, pixel art, and others), V3 is the minimum version that supports them.

## When to use

### Best For

- Design workflows that need consistent style across generations using the 20+ built-in presets
- Projects requiring native vector output for logos, icons, or print assets
- Text generation within images where multi-word copy needs precise positioning
- Illustration and character work where anatomical accuracy matters

### Consider Alternatives When

- You want maximum photorealism with natural skin, clean lighting, and fewer synthetic artifacts. Recraft V4 improves on V3 here
- You need print-ready, high-resolution output. Recraft V4 Pro targets that use case
- Budget is your primary constraint and you don't need the style library. Recraft V2 may suffice; compare per-image rates

## Best for

- **Consistent style presets:** Design workflows that use the 20+ built-in presets to keep output on-aesthetic across generations
- **Native vector output:** Projects that need scalable vector graphics for logos, icons, or print assets
- **Precise text positioning:** In-image text generation where multi-word copy must land exactly
- **Anatomically accurate illustration:** Character and figure work where correct proportions matter

## Consider alternatives

- **Maximum photorealism:** Recraft V4 improves natural skin, clean lighting, and reduces synthetic artifacts
- **Print-ready resolution:** Recraft V4 Pro targets high-resolution output for print production
- **Budget-first without presets:** Recraft V2 may suffice when the style library isn't needed, so compare per-image rates

## Frequently asked questions

### What style presets does Recraft V3 include?

Over 20 specialized styles spanning realistic portraits, digital illustrations, pixel art, vector graphics, and more. Each preset applies a consistent aesthetic without style descriptions in the prompt.

### Does Recraft V3 support vector output?

Yes. Recraft V3 generates scalable vector graphics directly. Use it for logos, icons, and print assets where resolution independence matters.

### How does text generation differ between V2 and V3?

V3 handles long multi-word text with precise positioning in the composition. V2 renders text accurately, but V3 extends this to longer copy and gives finer control over placement.

### What does anatomically correct output mean in practice?

More natural human proportions, realistic hands and faces, and correct body poses. You'll spend less time retouching the anatomical errors common in generated images.

### Is Recraft V3 a multimodal LLM?

No. Recraft V3 is a dedicated image generation model. It doesn't have a conversational context or text completion interface. Use `generateImage` from the AI SDK.

### How do I use Recraft V3 on AI Gateway?

Pass `recraft/recraft-v3` to `generateImage` from the AI SDK. AI Gateway routes the request to available providers automatically.

### What does Recraft V3 cost?

This page lists the current rates. Multiple providers can serve Recraft V3, so AI Gateway surfaces live pricing rather than a single fixed figure.

### When should I choose V3 over V4?

Choose V3 when style presets and vector output are central to your workflow and you don't need V4's photorealism improvements. If natural skin textures, clean lighting, and fewer synthetic artifacts matter more, evaluate V4.

## Links

- [Model page](https://vercel.com/ai-gateway/models/recraft-v3)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://www.recraft.ai/docs/recraft-models/recraft-V3)
- [Provider pricing](https://www.recraft.ai/docs/api-reference/pricing)