Recraft V4 Pro Serverless API

Print-ready 2K design images with legible in-image text.

PlaygroundAPI
Pricing
~20.89s
POST /v2/recraft-v4-pro · submit + poll
 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3import segmind
 4
 5# Async (v2): submit to the queue and block until COMPLETED.
 6# run() returns the final result dict (600s deadline, 1.0s poll by default).
 7result = segmind.run(
 8    "recraft-v4-pro",
 9    prompt="A tabletop board game box top for a cooperative deep-sea expedition game. Title 'ABYSS PROTOCOL' in bold condensed serif letters across the top, a smaller tagline 'descend, survive, resurface' beneath it, and a bottom banner reading '2-4 PLAYERS  AGES 12+  60 MIN'. Centered flat illustration of a brass diving bell descending past a glowing bioluminescent anglerfish, teal-to-indigo palette, mid-century poster illustration",
10    style_reference_urls=[],
11    size="2048x2048",
12    style_match="flexible",
13    colors=[],
14    background_color=None,
15    seed=-1,
16)
17print(result["status"])                      # COMPLETED
18print(result.get("output"))                  # model output (e.g. media URL)
19print(result["metrics"]["inference_time"])   # server compute seconds
20
21# --- Or submit + poll manually (track request_id, control the cadence) ---
22from segmind import SegmindClient, InferenceFailed, InferenceTimeout
23
24client = SegmindClient()                      # reads SEGMIND_API_KEY
25payload = {
26    "prompt": "A tabletop board game box top for a cooperative deep-sea expedition game. Title 'ABYSS PROTOCOL' in bold condensed serif letters across the top, a smaller tagline 'descend, survive, resurface' beneath it, and a bottom banner reading '2-4 PLAYERS  AGES 12+  60 MIN'. Centered flat illustration of a brass diving bell descending past a glowing bioluminescent anglerfish, teal-to-indigo palette, mid-century poster illustration",
27    "style_reference_urls": [],
28    "size": "2048x2048",
29    "style_match": "flexible",
30    "colors": [],
31    "background_color": None,
32    "seed": -1,
33}
34job = client.submit_async("recraft-v4-pro", **payload)
35print(job.request_id)                         # available immediately
36try:
37    result = job.wait(timeout=600, interval=1.0)
38except InferenceTimeout as e:
39    print("still running:", e.request_id)
40except InferenceFailed as e:
41    print("failed:", e.detail)

API Endpoint

POSThttps://api.segmind.com/v1/recraft-v4-pro

Parameters

promptrequired
string

Text describing the image to generate (up to 10,000 characters). Text you want rendered in the image can be quoted directly.

background_coloroptional
string

Preferred background color as a #RRGGBB hex value.

Default: null
colorsoptional
string[]

Up to 10 preferred colors as #RRGGBB hex values, e.g. #1E90FF.

Default: []
seedoptional
integer

Seed for reproducible generation. -1 picks a random seed.

Default: -1Range: -1 - 2147483647
sizeoptional
string

Width and height of the generated image in pixels. Auto lets Recraft pick from the prompt. The API also accepts a bare aspect ratio such as 16:9.

Default: "auto"
Allowed values (15 total):
Auto (from prompt)→"auto"
2048x2048 (1:1)→"2048x2048"
3072x1536 (2:1)→"3072x1536"
1536x3072 (1:2)→"1536x3072"
2560x1664 (3:2)→"2560x1664"
1664x2560 (2:3)→"1664x2560"
2432x1792 (4:3)→"2432x1792"
1792x2432 (3:4)→"1792x2432"
2304x1792 (5:4)→"2304x1792"
1792x2304 (4:5)→"1792x2304"
+5 more
style_matchoptional
string

How closely to follow the style reference images. Only used when style reference images are attached.

Default: "flexible"
Allowed values :
Flexible (match the vibe)→"flexible"
Precise (hold every detail)→"precise"
style_reference_urlsoptional
string[]

Optional 1-10 images (PNG, JPG or WEBP) whose look the generation should match: rendering technique, colors, texture and composition. A one-off style-creation fee is added when references are attached.

Default: []

Response Type

Returns: Text/JSON

Asynchronous requests (v2)

Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.

  1. 1
    POST /v2/recraft-v4-pro

    Submit — returns request_id, status_url, response_url

  2. 2
    GET /v2/requests/{id}/status

    Poll — until COMPLETED or FAILED

  3. 3
    GET /v2/requests/{id}

    Result — final response body

Status states

QUEUED— Accepted, waiting for a worker
PROCESSING— Running on a worker
COMPLETED— Done — result body is ready
FAILED— Errored (incl. content/RAI blocks)
  • A FAILED request is served as HTTP 422 — the body still carries the error detail.
  • An unknown or expired request_id returns HTTP 404.
  • Results are retained for 1 hour, then expire.
  • Content / RAI blocks surface as FAILED, not a separate state.
  • Track completion by polling the status endpoint.

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid parameters or request format

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out