Recraft AI Recraft V4.1 Pro Text To Vector API Documentation

Recraft AI Recraft V4.1 Pro Text To Vector API Documentation

Playground

Recraft V4.1 Pro Text to Vector is a fast AI vector generation model that creates premium editable vector images from text prompts. Ready-to-use REST inference API for logos, icons, illustrations, brand assets, scalable graphics, design systems, and professional text-to-vector workflows with simple integration, no coldstarts, and affordable pricing.

Features

Recraft V4.1 Pro Text-to-Vector generates premium editable vector images from natural-language prompts. It is designed for high-quality SVG creation workflows such as logo concepts, brand assets, icons, illustrations, marketing graphics, and other design tasks that benefit from scalable vector output.

Why Choose This?

• Premium vector generation Create polished editable vector images directly from text prompts.

• SVG output Generate scalable vector artwork that can be resized without losing quality.

• Simple prompt-based workflow Turn natural-language descriptions into vector graphics with minimal setup.

• Preset image sizing Use image_size presets for predictable output framing and composition.

• Production-ready generation Suitable for branding, illustration, marketing, UI assets, and other vector-first creative workflows.

Parameters

How to Use

1. Write your prompt — describe the subject, style, composition, and visual direction you want.
2. Choose image size (optional) — select the preset that best fits your intended layout.
3. Submit — run the model and download the generated vector image.

Example Prompt

A clean modern vector illustration of a mountain sunrise logo, geometric shapes, minimal color palette, premium outdoor brand style

Output

Returns one SVG vector image URL in the standard WaveSpeed prediction response.

Pricing

Pricing is a flat rate per image.

Billing Rules

• Each generated vector image costs $0.36
• Pricing is fixed per image
• image_size does not affect pricing

Best Use Cases

• Logo concepts — Generate editable vector directions for brand identity work.
• Brand graphics — Create scalable assets for marketing and design systems.
• Illustration — Produce vector-style artwork for commercial or editorial use.
• UI and icon assets — Generate clean scalable graphics for product and interface workflows.
• Marketing materials — Create vector visuals for ads, presentations, and publishing.

Pro Tips

• Be specific in your prompt about style, shape language, and composition.
• Mention terms like minimal, geometric, flat, icon-style, or brand illustration when relevant.
• Use concise but descriptive prompts for more controllable vector outputs.
• Start with the default size preset unless you need a specific layout.

Notes

• prompt is required.
• image_size defaults to square_hd.
• The model returns a single SVG vector image per request.
• Pricing is fixed at $0.36 per image.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "image_size": "1:1"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/recraft-ai/recraft-v4.1-pro/text-to-vector" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters