> ## Documentation Index
> Fetch the complete documentation index at: https://docs.magnific.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Recraft V4 – Text-to-Image API | Magnific API

> Generate design-ready images with Recraft V4. Best-in-class in-image text rendering for posters, signage and packaging, across eleven aspect ratios.

<Card title="Recraft V4" icon="wand-magic-sparkles">
  Design-oriented text-to-image generation with legible in-image text, across eleven fixed aspect ratios.
</Card>

Recraft V4 is a text-to-image API built for design work rather than photography: posters, signage, packaging and editorial layouts. Its main strength is rendering text that is actually readable and correctly spelled inside the image, which most diffusion models struggle with. For the same model at twice the linear dimensions, see <a href="/api-reference/text-to-image/recraft-v4-pro/overview">Recraft V4 Pro</a>; for the newer generation with quality tiers and a literal rendering mode, see <a href="/api-reference/text-to-image/recraft-v4-1/overview">Recraft V4.1</a>.

### Key capabilities

* **In-image text**: renders legible words and short phrases — signage, labels, headlines — reliably enough to use in finished design work
* **Design-first output**: composition, typography and layout rather than photographic realism
* **Eleven aspect ratios**: from `vertical_1_2` to `horizontal_2_1`, each with a documented pixel size
* **Optional prompt rewriting**: `enhance_prompt` is on by default and expands your prompt into a richer design brief, preserving any text the image must render. Turn it off for a deterministic input
* **Async processing**: every request returns a task ID immediately. Poll the task endpoint or supply `webhook_url` to be notified on completion

### Use cases

* **Posters and signage**: designs whose wording has to be readable and correctly spelled
* **Packaging mockups**: labels and boxes with real text rather than text-shaped noise
* **Editorial illustration**: article and newsletter art generated from a detailed brief
* **Brand assets**: key visuals where the headline or product name appears inside the image

### Generate images with Recraft V4

Submit a prompt to create a generation task. The API responds with a task ID; collect the result by polling or via webhook.

<div className="my-11">
  <Columns cols={2}>
    <Card title="POST /v1/ai/text-to-image/recraft-v4" icon="wand-magic-sparkles" href="/api-reference/text-to-image/recraft-v4/generate">
      Create a new image generation task
    </Card>

    <Card title="GET /v1/ai/text-to-image/recraft-v4" icon="list" href="/api-reference/text-to-image/recraft-v4/recraft-v4-tasks">
      List all Recraft V4 tasks with status
    </Card>

    <Card title="GET /v1/ai/text-to-image/recraft-v4/{task-id}" icon="magnifying-glass" href="/api-reference/text-to-image/recraft-v4/task-by-id">
      Get task status and results by ID
    </Card>
  </Columns>
</div>

### Parameters

| Parameter | Type | Required | Default | Description |
| - | - | - | - | - |
| `prompt` | `string` | Yes | - | Text description of the image to generate, up to 10,000 characters. Spell out any wording the design must contain |
| `aspect_ratio` | `string` | No | `square_1_1` | Shape of the output. See the size table below for the exact pixels each value produces |
| `enhance_prompt` | `boolean` | No | `true` | Rewrite the prompt with an LLM before generating. Text the image must render is preserved verbatim. Set to `false` to send the prompt exactly as written |
| `webhook_url` | `string` | No | - | URL called when the task completes |

### Output sizes

Recraft renders from a fixed set of sizes. The values below are the exact pixel dimensions each `aspect_ratio` produces, and they are **not always the mathematical ratio the name suggests** — `widescreen_16_9` renders 1344x768, which is 7:4.

| `aspect_ratio` | Output |
| - | - |
| `square_1_1` | 1024x1024 |
| `horizontal_2_1` | 1536x768 |
| `vertical_1_2` | 768x1536 |
| `standard_3_2` | 1280x832 |
| `portrait_2_3` | 832x1280 |
| `classic_4_3` | 1216x896 |
| `traditional_3_4` | 896x1216 |
| `social_5_4` | 1152x896 |
| `social_post_4_5` | 896x1152 |
| `widescreen_16_9` | 1344x768 |
| `social_story_9_16` | 768x1344 |

### Pricing

A flat price per image. One image is generated per request. Recraft V4 Pro renders the same aspect ratios at twice the linear dimensions for a higher price.

The endpoint reference pages above are generated from the OpenAPI specification and are the authoritative, complete parameter list.

## Frequently Asked Questions

<AccordionGroup>
  <Accordion title="What is Recraft V4 and how does it work?">
    Recraft V4 is a text-to-image API aimed at design output rather than photography. You submit a text prompt and receive a task ID immediately. Poll the task endpoint or configure a webhook to receive the generated image when processing completes.
  </Accordion>

  <Accordion title="Is Recraft V4 good at rendering text inside images?">
    Yes — it is the main reason to choose it. Short, specific strings such as a product name, a headline or a sign work best. Put the exact wording in quotes inside your prompt.
  </Accordion>

  <Accordion title="What is the difference between Recraft V4 and V4 Pro?">
    Same model family and the same parameters; V4 Pro renders every aspect ratio at twice the linear dimensions — four times the pixels — and costs more credits per image.
  </Accordion>

  <Accordion title="Why does widescreen_16_9 not return a 16:9 image?">
    Recraft generates from a fixed set of sizes, and the preset names are approximate. `widescreen_16_9` returns 1344x768, which is 7:4. The size table above lists the exact dimensions for every value.
  </Accordion>

  <Accordion title="How many images can I generate per request?">
    One. Submit multiple requests to generate variations.
  </Accordion>

  <Accordion title="What are the rate limits for Recraft V4?">
    Rate limits depend on your subscription tier. See [Rate Limits](/ratelimits) for current limits.
  </Accordion>

  <Accordion title="How much does Recraft V4 cost?">
    See the [Pricing page](/pricing) for current rates and subscription options.
  </Accordion>
</AccordionGroup>

## Best practices

* **Quote the text**: put the exact string you want rendered in quotes inside the prompt, and keep it short
* **Describe the design, not just the subject**: layout, palette and typography style guide the output more than keyword lists
* **Choose the ratio by pixels**: use the size table rather than the preset name, which is approximate
* **Turn off `enhance_prompt` for reproducibility**: when A/B testing prompts, the rewrite adds a variable you do not control
* **Production integration**: use `webhook_url` instead of polling for scalable applications
* **Error handling**: implement retry logic with exponential backoff for 503 errors

## Related APIs

* **[Recraft V4 Pro](/api-reference/text-to-image/recraft-v4-pro/overview)**: the same model at twice the linear dimensions
* **[Recraft V4.1](/api-reference/text-to-image/recraft-v4-1/overview)**: the newer generation, with quality tiers and a literal `utility` mode
* **[GPT Image 2](/api-reference/text-to-image/gpt-image-2/overview)**: OpenAI generation, also strong at in-image text


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.