Recraft AI Recraft V4 Text To Image API Documentation

Recraft AI Recraft V4 Text To Image API Documentation

Playground

Recraft V4 generates high-quality images from text prompts with color palette control. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Recraft V4 is a state-of-the-art text-to-image model that generates stunning, high-quality images from text descriptions. With flexible aspect ratios and a built-in Prompt Enhancer, it delivers professional-grade visuals for any creative project.

Why Choose This?

• V4 quality Latest Recraft architecture delivering superior visual fidelity and prompt adherence.

• Flexible aspect ratios Multiple options including 1:1, 16:9, 9:16, 4:3, and 3:4 to fit any platform or use case.

• Prompt Enhancer Built-in tool to automatically improve your descriptions for better results.

• Affordable pricing Just $0.04 per image for professional-quality output.

Parameters

How to Use

1. Write your prompt — describe the image in detail, including style, lighting, and composition.
2. Choose aspect ratio — select the format that fits your needs.
3. Use Prompt Enhancer (optional) — click to automatically refine your description.
4. Run — submit and download your generated image.

Pricing

Best Use Cases

• Social Media Content — Create eye-catching visuals for Instagram, TikTok, and more.
• Marketing & Ads — Generate professional images for campaigns and promotions.
• Concept Art — Visualize ideas and creative concepts quickly.
• E-commerce — Produce product imagery and lifestyle shots.
• Personal Projects — Bring your creative visions to life.

Pro Tips

• Be specific in your prompts — include camera settings, lighting, and style references for best results.
• Use cinematic language like “shot on Canon EOS R5, 85mm f/1.4, natural lighting, film grain” for photorealistic output.
• Try the Prompt Enhancer to automatically improve your descriptions.
• Match aspect ratio to your target platform: 9:16 for Stories/Reels, 16:9 for YouTube thumbnails, 1:1 for feeds.

Notes

• Prompt is the only required field.
• Ensure your prompts comply with content guidelines.

Related Models

• Recraft V4 Pro Text-to-Image — Pro tier with enhanced quality.
• Recraft V4 Text-to-Vector — Generate vector graphics from text.
• Recraft V4 Pro Text-to-Vector — Pro tier vector generation.

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",
  "size": "1024*1024"
}
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/text-to-image" \
  -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