Recraft V4 Pro Vector API

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name	recraft-v4-pro/text-to-vector
Type	Image generation (text-to-vector SVG)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

Recraft V4 Pro Vector: the same description produces a more detailed editable SVG for finished logos, complex icons and vector illustration.

Production guidance

For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
Result URLs expire — copy the output to your own storage once the task succeeds.
The output is an SVG vector file. If your pipeline needs raster images, rasterize it after download; do not treat the bytes as JPEG/PNG.

Best suited for

Finished logos

Brand marks with layered structure, negative space and precise contours.

promptcolors

Complex icon sets

Multi-object icons in one visual language that hold up when enlarged.

promptimage_size

Detailed vector illustration

Posters, packaging and editorial art ready for prepress.

prompt

Request parameters

POST https://api.hiapi.ai/v1/tasks

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "recraft-v4-pro/text-to-vector",
  "input": {
    "prompt": "A detailed flat vector illustration of a coastal town at golden hour: terraced houses on a cliff, fishing boats in the harbor, seagulls, layered waves. Limited palette of coral, navy, sage and cream, crisp geometric shapes, strong silhouettes, no gradients",
    "image_size": "square_hd"
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "recraft-v4-pro/text-to-vector",
  "input": {
    "prompt": "A detailed flat vector illustration of a coastal town at golden hour: terraced houses on a cliff, fishing boats in the harbor, seagulls, layered waves. Limited palette of coral, navy, sage and cream, crisp geometric shapes, strong silhouettes, no gradients",
    "image_size": "square_hd"
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "recraft-v4-pro/text-to-vector",
  "input": {
    "prompt": "A detailed flat vector illustration of a coastal town at golden hour: terraced houses on a cliff, fishing boats in the harbor, seagulls, layered waves. Limited palette of coral, navy, sage and cream, crisp geometric shapes, strong silhouettes, no gradients",
    "image_size": "square_hd"
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value recraft-v4-pro/text-to-vector.

example recraft-v4-pro/text-to-vector

input object required

Business parameters.

prompt string required

Vector artwork description: subject, shapes, style and any text to draw. 1–10,000 characters.

image_size enum optional

Canvas ratio preset. The preset sets the canvas orientation and ratio; the SVG output scales without loss.

default square_hd enum: square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9

colors array optional

Preferred palette as an array of RGB objects; each object contains r, g and b from 0 to 255.

r integer required

0–255, red

g integer required

0–255, green

b integer required

0–255, blue

background_color object optional

Preferred background color as an RGB object; r, g and b range from 0 to 255.

r integer required

0–255, red

g integer required

0–255, green

b integer required

0–255, blue

callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; HTTPS URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Callback trigger timing. Use final.

default final enum: final

Example requests

Set a brand palette

colors sets deep green and sand, while background_color sets cream; the SVG paths stay within that palette.

Request body

{
  "model": "recraft-v4-pro/text-to-vector",
  "input": {
    "prompt": "A minimal geometric mountain mark for an outdoor brand, flat vector, centered",
    "image_size": "square_hd",
    "colors": [
      {
        "r": 22,
        "g": 61,
        "b": 52
      },
      {
        "r": 232,
        "g": 212,
        "b": 178
      }
    ],
    "background_color": {
      "r": 250,
      "g": 246,
      "b": 238
    }
  }
}

Getting the result

The response returns a taskId immediately without waiting for generation to finish.
In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
When status=success, download the SVG file from output[].url.
Open the file in a browser, Figma, Illustrator or Sketch. SVG is a text-based vector format.
When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

What is the Pro tier best for?

Finished logos, complex icon sets, detailed vector illustration and brand assets that need one visual language.

How is it different from the standard V4 Vector?

Inputs are identical. Pro spends more effort on contours, layers and small structures for production-ready results; V4 is better for fast options.

What format is the output?

An editable SVG vector file, one file per request at output[].url in the task result.

Which canvas sizes are supported?

image_size accepts square_hd (default), square, portrait_4_3, portrait_16_9, landscape_4_3 and landscape_16_9.

Can I specify brand colors?

Yes. Pass colors (an array of RGB objects) and background_color (one RGB object), each channel 0–255.

Can the result be edited in design tools?

Yes. SVG opens in Figma, Illustrator, Sketch and similar tools for node, color and text edits and export at any size.

Do I need a reference image?

No. It is a text-to-vector model.

How is it billed?

Per output SVG file, one file per request. See the live pricing page for the current rate.