Recraft AI Recraft V4.1 Flash Text To Image API Documentation

Recraft AI Recraft V4.1 Flash Text To Image API Documentation

Playground

Recraft V4.1 Flash Text-to-Image generates high-quality raster images from text prompts for photography, illustrations, creative compositions, marketing visuals, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Recraft V4.1 Flash Text-to-Image generates raster images directly from text prompts for fast creative exploration. Describe the subject, composition, lighting, and visual style, then choose a square, portrait, or landscape aspect ratio to generate the final image.

It is suited to photography, illustration, mixed-media compositions, product concepts, editorial visuals, and other workflows where fast text-to-image generation is useful.

Why Choose This?

• Fast text-to-image generation
  Turn natural-language descriptions into finished raster images.

• Flexible visual styles
  Create photography, illustrations, mixed-media compositions, and other visual directions through prompting.

• Creative iteration
  Quickly explore different subjects, compositions, lighting setups, and styles.

• Multiple aspect ratios
  Generate square, portrait, or landscape images for different publishing and design needs.

• Simple workflow
  Only a text prompt is required, making the endpoint easy to integrate into image-generation pipelines.

Parameters

How to Use

1. Write a prompt — Describe the subject, composition, lighting, colors, and visual style.
2. Choose aspect ratio optional — Select a square, portrait, or landscape layout, or keep the default 1:1.
3. Submit — Generate the image.
4. Retrieve the result — Access the generated raster image from the prediction response.

Pricing

Pricing is fixed at $0.008 per generated image.

Best Use Cases

• Product concepts — Explore product ideas, presentation styles, and campaign imagery.
• Editorial visuals — Generate photography-style or illustrative images for articles and publications.
• Marketing creatives — Create campaign concepts, promotional graphics, and social media imagery.
• Illustration — Generate stylized or descriptive artwork directly from text.
• Mixed-media concepts — Explore compositions that combine different visual treatments and aesthetics.
• Rapid visual exploration — Test multiple creative directions quickly before final production.

Pro Tips

• Describe the main subject and composition before adding style details.
• Include lighting, color palette, environment, and mood when they matter to the result.
• Use 16:9 or 4:3 for landscape compositions.
• Use 9:16 or 3:4 for portrait-oriented content.
• Keep the prompt focused when you want stronger control over the main subject and composition.
• Iterate on prompt wording to explore different visual directions quickly.

Notes

• aspect_ratio defaults to 1:1.
• Supported aspect ratios are 1:1, 16:9, 9:16, 4:3, and 3:4.
• Each successful request generates one raster image.
• This endpoint is for text-to-image generation, not image editing or vector generation.
• Custom dimensions and structured color controls are not exposed in this configuration.

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",
  "aspect_ratio": "1:1"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/recraft-ai/recraft-v4.1-flash/text-to-image" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters