---
title: Recraft V4 Styles Pro Vector | Runware Docs
url: https://runware.ai/docs/models/recraft-v4-styles-pro-vector
description: Premium style-consistent SVG generation for high-end brand and design systems
---
# Recraft V4 Styles Pro Vector

![Recraft V4 Styles Pro Vector](https://assets.runware.ai/covers/recraft-v4-styles-pro-vector.jpg)

Recraft V4 Styles Pro Vector is the premium vector model in the V4 Styles family. It pairs reusable reference-based style creation with SVG output for workflows that need stronger detail retention and more polished scalable assets. It is well suited to brand systems, icon libraries, packaging graphics, editorial illustration systems, and other vector-first pipelines where a consistent visual identity needs to carry across many generated assets without training a dedicated custom model.

- **Status**: live
- **ID**: `recraft:v4@styles-pro-vector`
- Try in Playground
- **Creator**: Recraft
- **Release Date**: August 13, 2026
- **Capabilities**: Text to Image, Image to Image, Vectorize, Checkpoint

## Pricing

$0.125 per run · ~41s per request

**4 example generations**

- [vectorize](https://runware.ai/docs/models/recraft-v4-styles-pro-vector/examples#example-food-spectrometer-lifestyle-illustration): `$0.125` (~41s)
- [vectorize](https://runware.ai/docs/models/recraft-v4-styles-pro-vector/examples#example-wastewater-outbreak-detection-explainer): `$0.125` (~1m 45s)
- [vectorize](https://runware.ai/docs/models/recraft-v4-styles-pro-vector/examples#example-subsea-cable-crew-shirt-graphic): `$0.125` (~35s)
- [vectorize](https://runware.ai/docs/models/recraft-v4-styles-pro-vector/examples#example-street-sweeper-recruitment-campaign-illustration): `$0.125` (~41s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Provide exactly one of: `inputs.styleId`, `inputs.referenceImages`.

---

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `2K (1:1)` | `2048x2048` |
| `2K (2:1)` | `3072x1536` |
| `2K (1:2)` | `1536x3072` |
| `2K (3:2)` | `2560x1664` |
| `2K (2:3)` | `1664x2560` |
| `2K (4:3)` | `2432x1792` |
| `2K (3:4)` | `1792x2432` |
| `2K (5:4)` | `2304x1792` |
| `2K (4:5)` | `1792x2304` |
| `2K (6:10)` | `1664x2688` |
| `2K (14:10)` | `2560x1792` |
| `2K (10:14)` | `1792x2560` |
| `2K (16:9)` | `2688x1536` |
| `2K (9:16)` | `1536x2688` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `vectorize`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Image output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-outputformat)

- **Type**: `string`
- **Default**: `SVG`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`SVG\`: Scalable Vector Graphics.

**Allowed values**: `SVG`

### [webhookURL](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [ttl](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [referenceImages](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `10`
- **File size (each)**: `up to 10 MB`
- **File size (total)**: `up to 64 MB`
- **Size (each)**: `256 px or more`

List of reference images (UUID, URL, Data URI, or Base64).

### [styleId](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-inputs-styleid)

- **Path**: `inputs.styleId`
- **Type**: `string`
- **Format**: `UUID v4`

Identifier of an existing style to apply.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `recraft:v4@styles-pro-vector`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `10000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-width)

- **Type**: `integer`
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-height)

- **Type**: `integer`
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [backgroundColor](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-settings-backgroundcolor)

- **Path**: `settings.backgroundColor`
- **Type**: `object (1 property)`

Background color used for the generation.

**Learn more** (1 resource):

- [Color Palettes](https://runware.ai/docs/models/recraft-v4-1/guides/color-palettes) (learn)

#### [rgb](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-settings-backgroundcolor-rgb)

- **Path**: `settings.backgroundColor.rgb`
- **Type**: `array of integers`
- **Required**: true
- **Min**: `0`
- **Max**: `255`
- **Min items**: `items: 3`

Color as `[red, green, blue]` array.

### [colors](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-settings-colors)

- **Path**: `settings.colors`
- **Type**: `array of objects (1 property)`

Colors defining the palette for the generation.

**Learn more** (1 resource):

- [Color Palettes](https://runware.ai/docs/models/recraft-v4-1/guides/color-palettes) (learn)

#### [rgb](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-settings-colors-rgb)

- **Path**: `settings.colors.rgb`
- **Type**: `array of integers`
- **Required**: true
- **Min**: `0`
- **Max**: `255`
- **Min items**: `items: 3`

Color as `[red, green, blue]` array.

### [styleMatch](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#request-settings-stylematch)

- **Path**: `settings.styleMatch`
- **Type**: `string`
- **Default**: `precise`

How closely the style is followed. Overrides the match value stored on the style for this request.

**Allowed values**:

- `precise` Follows the style meticulously.
- `flexible` Matches the general look of the style.

## Response Parameters

### [taskType](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `vectorize`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [imageUUID](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#response-imageuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#response-imageurl)

- **Type**: `string`
- **Format**: `uri`

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#response-imagedatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output image.

### [cost](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

### [outputs](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#response-outputs)

- **Path**: `outputs.styleId`
- **Type**: `object (1 property)`

Generated output artifacts.

#### [styleId](https://runware.ai/docs/models/recraft-v4-styles-pro-vector#response-outputs-styleid)

- **Path**: `outputs.styleId`
- **Type**: `string`

The ID of the style applied to the generation. Can be used to reuse the style in later requests.

## Examples

### vectorize (vectorize)

![Food Spectrometer Lifestyle Illustration](https://assets.runware.ai/examples/recraft-v4-styles-pro-vector/b701239f-1f13-48e2-99b9-9a13c9e83339.svg)

```json
{
  "taskType": "vectorize",
  "taskUUID": "68465ff4-d854-41e7-a6a5-2061d5370084",
  "model": "recraft:v4@styles-pro-vector",
  "positivePrompt": "Create a finished square product-lifestyle illustration for the launch campaign of a portable food-authentication instrument. Use all three reference images only to synthesize their shared visual design language: polished premium vector artwork, crisp rounded geometry, selective deep-ink contours, layered flat color, controlled shadow grain, elegant three-quarter perspective, and strong diagonal light. Do not reproduce, trace, or borrow the subjects or exact compositions of the references.\n\nShow a saffron quality specialist using a compact handheld near-infrared spectrometer at a cooperative grading table in La Mancha, Spain. The hero product is a palm-sized matte cobalt-blue device with a softly rounded rectangular body, one circular sensor aperture surrounded by a small amber status ring, a single side button, and no logo or readable interface. Place it prominently in the lower-center foreground, held naturally a few centimeters above a shallow brass tray filled with vivid crimson saffron threads. The specialist's other hand gently separates a small sample with slim stainless-steel tweezers. Make the product silhouette, sensor end, hand grip, and relationship to the saffron immediately legible.\n\nBuild an authentic working environment around the hero action: cream plaster walls, a dark wood grading table, several unbranded glass sample jars, a precision scale, folded linen, a ceramic cup, and softly simplified drying racks in the background. Include a second worker farther back sorting saffron, subordinate in scale and detail. Warm late-afternoon sunlight enters from a high side window, casting long geometric shadows across the table and creating a focused amber glow around the crimson sample. Use a disciplined palette led by cobalt blue, saffron gold, warm cream, oxblood red, charcoal, and small brass accents.\n\nCompose as a sophisticated commercial in-scene product image rather than an instructional diagram: intimate waist-level viewpoint, dynamic diagonal flow from the window to the device and tray, clear foreground hero, layered middle ground, and an uncluttered background. Preserve realistic hand anatomy and credible instrument proportions while simplifying forms into clean scalable vector shapes. Rich detail without photorealism, polished edges, subtle depth, restrained texture, confident negative space, no lettering, no labels, no logos, no borders, no interface mockup, and no photographic effects.",
  "width": 2048,
  "height": 2048,
  "settings": {
    "styleMatch": "precise"
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/2bb73efb-5e5e-4c64-a0ff-ebf40654f95a.jpg",
      "https://assets.runware.ai/assets/inputs/4e437f7e-b101-46cd-9b23-059da4e7e7d1.jpg",
      "https://assets.runware.ai/assets/inputs/20157eb6-7131-4862-bc38-0988d1d235f0.jpg"
    ]
  }
}
```

---

### vectorize (vectorize)

![Wastewater Outbreak Detection Explainer](https://assets.runware.ai/examples/recraft-v4-styles-pro-vector/993bc9ca-e17d-4c90-8576-e3abf9a931bf.svg)

```json
{
  "taskType": "vectorize",
  "taskUUID": "064329d0-8166-412f-8bad-caba22094f40",
  "model": "recraft:v4@styles-pro-vector",
  "positivePrompt": "Create a finished 2048x2048 square public-health explainer infographic titled “WASTEWATER EARLY WARNING.” Use the three reference images only to establish their shared visual language—premium science-museum editorial design, disciplined geometry, axonometric cutaways, rounded technical lines, modular callouts, restrained screen-print texture, strong hierarchy, and coherent color coding. Do not reproduce or trace any reference subject or composition.\n\nExplain how municipal wastewater surveillance detects a community outbreak before clinical case counts rise. Build one continuous, easy-to-follow journey across a stylized city cross-section, arranged in a broad S-shaped flow with six clearly separated stages. Stage 01: several homes, an apartment building, a school, and a clinic feed into a shared underground sewer; label “COMMUNITY SIGNAL.” Stage 02: an automatic sampler beside a wastewater treatment inlet collects a composite bottle; label “24-HOUR SAMPLE.” Stage 03: a courier carries the sealed chilled bottle to a public-health laboratory; label “COLD TRANSPORT.” Stage 04: a laboratory technician concentrates genetic material using tubes, pipettes, a centrifuge, and a clean molecular testing bench; label “LAB ANALYSIS.” Stage 05: abstract RNA fragments resolve into a simple rising signal chart and three pathogen symbols; label “TREND DETECTED.” Stage 06: public-health teams use the signal to guide testing, staffing, and community outreach; label “EARLIER ACTION.” Connect every stage with an unmistakable cyan pipeline or arrow so the process reads instantly from upper left to lower right.\n\nInclude a compact bottom legend with three concise lines: “ONE SAMPLE • THOUSANDS OF PEOPLE,” “ANONYMOUS • COMMUNITY-LEVEL DATA,” and “TRENDS • NOT INDIVIDUAL DIAGNOSES.” Add a small comparison graphic showing a lime wastewater signal curve rising several days before a coral clinical-case curve, captioned “ADVANCE NOTICE.” Keep all wording exactly as provided and avoid additional paragraphs.\n\nRender as polished scalable vector artwork with a deep aubergine field, warm ivory type and buildings, cyan water and infrastructure lines, acid-lime detection signals, coral intervention accents, and occasional pale lavender details. Use flat layered shapes, precise negative space, consistent rounded line weights, simplified human figures, and subtle halftone grain confined inside selected shapes. Clear educational tone, scientifically credible equipment, accessible iconography, high contrast, balanced square composition, generous margins, no logos, no fake organization, no website, no app interface, no photorealism, and no decorative elements unrelated to the explanation.",
  "width": 2048,
  "height": 2048,
  "settings": {
    "styleMatch": "precise"
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/c1755319-7b50-4ea5-9f17-919eb18a2995.jpg",
      "https://assets.runware.ai/assets/inputs/1662f5c5-bc07-48dd-a6a1-035c374d95f5.jpg",
      "https://assets.runware.ai/assets/inputs/4a588f98-d8b6-4f8a-b194-d02e9d67282e.jpg"
    ]
  }
}
```

---

### vectorize (vectorize)

![Subsea Cable Crew Shirt Graphic](https://assets.runware.ai/examples/recraft-v4-styles-pro-vector/94f5bbde-c8c6-4b5f-9212-132c3a3bce3a.svg)

```json
{
  "taskType": "vectorize",
  "taskUUID": "15664eda-30bc-4af2-a4be-227780530080",
  "model": "recraft:v4@styles-pro-vector",
  "positivePrompt": "Create a finished square apparel graphic for the crew of a subsea fiber-optic cable repair vessel, rendered as polished scalable vector artwork in the coherent visual style established by the three reference images. Do not reproduce or trace any reference composition or subject; apply their shared chunky neo-woodcut geometry, bold cream keylines, selective engraved hatching, simplified technical detail, rounded badge framing and disciplined five-color screen-print treatment to this entirely new subject.\n\nShow a dramatic ocean cross-section. In the upper half, a specialized cable repair ship travels in profile across rolling waves, with a working stern gantry, cable drums and deck crane clearly simplified into strong readable shapes. A thick fiber-optic cable descends from the vessel through the water and sweeps into the lower half, where a compact work-class ROV uses articulated arms to inspect an exposed repeater housing on the seabed. Include restrained supporting details such as bubbles, contour lines, small fish silhouettes, rock strata and a subtle beam of light from the ROV, all kept secondary and screen-print friendly. Make the cable itself a strong visual path connecting ship, ROV and seabed.\n\nIntegrate exact, highly legible display lettering into the badge: “KEEP THE WORLD CONNECTED” arched across the top and “SUBSEA CABLE CREW” across the bottom. Use sturdy condensed block capitals with slight maritime utility character, not a logo and no other words, numbers or symbols. Balance the lettering and illustration as one professional garment graphic.\n\nUse only midnight navy, warm cream, seafoam green, safety orange and dusty lavender. Flat spot-color fills only, no gradients, no photorealism, no soft shadows and no transparency effects. Build clean closed vector shapes, substantial outlines, controlled negative space and limited hatching that will survive screen printing. Center the complete composition with ample margin on all sides. Strong silhouette and readability from a distance, rugged but optimistic technical mood. Standalone print artwork only, not a T-shirt mockup, not a product photograph and not a presentation board.",
  "width": 2048,
  "height": 2048,
  "settings": {
    "styleMatch": "precise"
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/cb5fadeb-6fb1-44db-9270-917eeb562694.jpg",
      "https://assets.runware.ai/assets/inputs/8acabb9d-5c18-4869-854f-18edbfb0f5b9.jpg",
      "https://assets.runware.ai/assets/inputs/9f62198f-446a-4d0b-ab6e-b487d0391950.jpg"
    ]
  }
}
```

---

### vectorize (vectorize)

![Street Sweeper Recruitment Campaign Illustration](https://assets.runware.ai/examples/recraft-v4-styles-pro-vector/5cab3437-a7c0-4241-8f85-13c760e53ef7.svg)

```json
{
  "taskType": "vectorize",
  "taskUUID": "57d4d4e8-e0ea-4427-b526-76bb18fed78e",
  "model": "recraft:v4@styles-pro-vector",
  "positivePrompt": "Create finished square recruitment-campaign key art for a municipal public works department, using the three reference images only to establish their shared visual language. Do not reproduce, trace or directly remix any reference subject, character, pose or composition. Render a new subject as polished anime-inspired vector artwork: a confident woman operating a compact street sweeper during the blue hour before sunrise. Show the orange utility vehicle from a dramatic low three-quarter curbside angle as it rounds a corner, with the operator clearly visible through the wide cab window wearing a practical high-visibility work jacket and headset. Emphasize the machine's rotating circular brushes, articulated cleaning hardware and clean geometric body panels; sweeping arcs of dry leaves and small paper scraps create energetic manga-like motion without making the scene chaotic. The street behind the vehicle is visibly clean, with quiet apartment facades, young street trees, bike racks and soft dawn windows establishing a real neighborhood rather than a futuristic city. Give the worker an alert, capable expression and heroic visual presence while keeping the occupation and machinery believable. Match the references' coherent design system: expressive contemporary anime character drawing, thick deep-indigo contour lines, precise flat vector shapes, angular cel-shaded lighting, selective halftone texture in background areas, bold diagonal rhythm, crisp negative space and carefully simplified environmental detail. Use a restrained palette of coral orange, electric mint, pale cream and deep indigo, with a small warm sunrise accent. Strong central silhouette, balanced 2048x2048 composition, clean edges suitable for scalable campaign artwork. No words, captions, logos, emblems, interface elements, mockup framing or photorealistic textures.",
  "width": 2048,
  "height": 2048,
  "settings": {
    "styleMatch": "precise"
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/cb8bcde8-d98f-4e9a-a72a-ac7df98db0eb.jpg",
      "https://assets.runware.ai/assets/inputs/6d5395b3-3aa7-4a02-af8d-9b4eba4d7fff.jpg",
      "https://assets.runware.ai/assets/inputs/744c25ce-ca77-49ca-b34a-34c5ff2cae25.jpg"
    ]
  }
}
```