Recraft

Recraft V4.1

recraft-v4.1-flash/text-to-image

A production-oriented model for generating design assets, with native editable SVG vector output. It reliably produces images from short prompts and is well suited to icons, typography, and brand illustrations.

recraft-v4.1-flash/text-to-image recraft-v4.1/text-to-image

Try recraft-v4.1-flash/text-to-image

Input

Colors

Showcases

View all showcases

Output

image

Fill in the parameters and run — results show up here.

Pricing

recraft-v4.1-flash/text-to-image per image

Unit Price	$0.010

Positioning Overview

Recraft V4.1 Flash is the fast tier of the Recraft V4.1 series for text-to-image generation. It is accessed through the unified HiAPI.ai interface and produces images from text prompts. It continues the series' design-oriented approach, delivering high-quality results on illustration, icon, and brand visual tasks, and can achieve relatively stable visual results with short prompts. It is suitable for developers and design teams that need batch image generation and want to embed the generation step into content automation workflows.

Core Highlights

Design asset-oriented visual style — Compared with general-purpose image models, it leans more toward production-ready design outputs such as icons, illustrations, and brand visuals, rather than previews that only look good.
Stable results from short prompts — A brief description is enough to obtain a fairly clear composition and aesthetic direction, reducing the prompt engineering burden of repeated parameter tuning.
Optional palette and background color control — Supports specifying preferred colors and background color via RGB values, making it easy to keep a consistent style across multiple images in a series.
Multiple aspect ratio and size presets — Provides six size presets in square, 4:3, and 16:9, in both landscape and portrait, covering common layouts such as social images, vertical posters, and banners.

Capabilities

Text-to-image generation: Generates images from a text prompt of up to 10,000 characters, which can describe the subject, style, and scene details. It is suitable for integration into automated image generation workflows.

Color and background color control: Preferred palettes and background colors can be specified via RGB objects, keeping batch-generated assets consistent under the same visual specification.

Output size presets: Built-in size presets in multiple tiers for square and both landscape and portrait ratios. Select the layout directly according to the placement during the call, with no post-cropping required.

Use Cases

Batch generation of series assets for brand and marketing teams — Batch-produce campaign images and promotional assets with unified colors and size presets, ready for ad placements and content scheduling.
Interface illustrations and graphics in UI/UX design — Generate interface illustrations and decorative graphics from brief descriptions, usable as assets in design files for product pages and prototypes.
Image generation in content automation pipelines — Connect image generation calls to publishing systems to automatically generate images based on article or product information, reducing manual one-by-one production.

Limitations and Selection Advice

It is positioned toward design assets and concept exploration, and does not cover all image generation needs. Generated results, especially colors and composition, are still recommended for human review before formal delivery. If higher-quality single-image output is required, consider the non-Flash version of the same series. This tier emphasizes fast image generation, so extreme detail and complex realistic scenes should be evaluated with caution.

What's new

View changelog →

New model New model available: recraft-v4.1-flash/text-to-image Nov 3, 2026
New model Added recraft-v4.1-flash/text-to-image documentation Oct 16, 2026

Frequently asked questions

View all FAQs →

How is Recraft V4.1 different from V4.1 Flash?

V4.1 focuses on detail and finish; Flash is faster and good for drafts in bulk.
Which sizes are supported?

image_size accepts square_hd (default), square, portrait_4_3, portrait_16_9, landscape_4_3 and landscape_16_9.
How do I set colors?

Pass colors (an array of RGB objects) and background_color (one RGB object) through the API, each channel 0–255. The online Playground does not show these two fields yet.
Are the colors followed strictly?

colors is a preferred palette and the image will lean toward it; if the prompt names clearly conflicting colors, the result may mix both.

Create a generation task

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

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.

Idempotency-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.

Body

modelstringRequired

Current fixed value: recraft-v4.1-flash/text-to-image

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for recraft-v4.1-flash/text-to-image and route default — see the parameter table below.

colorsarrayOptional

Preferred color palette, an array of RGB color objects, where each object's channel values range from 0 to 255; used to constrain the dominant tones of the generated image.

Array [ object ]

Array items

bintegerRequiredmin 0max 255

The blue channel value of a single color in the palette, an integer from 0 to 255.

gintegerRequiredmin 0max 255

The green channel value of a single color in the palette, an integer from 0 to 255.

rintegerRequiredmin 0max 255

The red channel value of a single color in the palette, an integer from 0 to 255.

promptstringRequiredminLength 1maxLength 10000

A textual description of the image to be generated, i.e., the prompt.

image_sizestringOptionalDefault: "square_hd"

Output size preset, given as a preset name in string form; defaults to square_hd.

Options:square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9

background_colorobjectOptional

Preferred background color, represented by a single RGB color object, with each channel value ranging from 0 to 255.

bintegerRequiredmin 0max 255

The blue channel value of the background color, an integer from 0 to 255.

gintegerRequiredmin 0max 255

The green channel value of the background color, an integer from 0 to 255.

rintegerRequiredmin 0max 255

The red channel value of the background color, an integer from 0 to 255.

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.

urlstringRequired

Required when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.

whenstringOptionalDefault: "final"

Only final is supported today — notified on both success and fail.

Options:final

storagestringOptionalDefault: "temp"

Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.

Options:temppersistent

Request examples

# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer $HIAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "recraft-v4.1-flash/text-to-image",
  "input": {
    "prompt": "…",
    "image_size": "square_hd"
  }
}'

const res = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "recraft-v4.1-flash/text-to-image",
    input: {
      "prompt": "…",
      "image_size": "square_hd"
    }
  }),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } }

import os, requests

res = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
    json={
        "model": "recraft-v4.1-flash/text-to-image",
        "input": {
          "prompt": "…",
          "image_size": "square_hd"
        }
    },
)
print(res.json())  # { code, message, data: { taskId } }

200 OK

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
  }
}

400 Bad Request

{
  "code": 400,
  "message": "invalid request",
  "data": null,
  "error_code": "INVALID_REQUEST"
}

Get task detail

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

queued Queued, not started yet. handling Being processed. archiving Processing finished, artifacts being prepared. success Terminal: completed, artifacts available (output returned). fail Terminal: failed (error returned). After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix seconds when the task reached a terminal state; fixed to 0 while not terminal.

outputarrayOptional

Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).

Array [ object ]

Array items

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error description.

Response examples

Success

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
    "model": "happyhorse-1-0",
    "status": "success",
    "created": 1777282033,
    "completed": 1777282099,
    "output": [
      {
        "url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
        "type": "video",
        "expireAt": 1777886899
      }
    ]
  }
}

Processing (non-terminal)

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "archiving",
    "created": 1777282033,
    "completed": 0
  }
}

Failed

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "fail",
    "created": 1777282033,
    "completed": 1777282099,
    "error": {
      "code": "TASK_FAILED",
      "message": "task failed"
    }
  }
}