Runwayml Gen4 Turbo API Documentation

Runwayml Gen4 Turbo API Documentation

Playground

RunwayML Gen4 Turbo is an image-to-video model that generates high-quality videos from images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Bring your images to life with AI-powered video generation. Runway Gen4 Turbo transforms static images into dynamic videos based on your text descriptions — perfect for creating cinematic motion, animated scenes, and engaging visual content.

Why It Looks Great

• Image-to-video synthesis: Animates your source image with natural, fluid motion guided by your prompt.
• Prompt Enhancer: Built-in tool to refine and improve your text descriptions for better results.
• Flexible aspect ratios: Supports 16:9, 4:3, 1:1, 3:4, and 9:16 for any output format.
• High-quality motion: Generates smooth, realistic movement that respects the original image composition.
• Turbo speed: Optimized for fast generation without compromising visual quality.

Parameters

How to Use

1. Write your prompt — describe the motion, action, and atmosphere you want in the video.
2. Use Prompt Enhancer (optional) — click the button to refine your description for better results.
3. Upload your image — drag and drop or paste a public URL.
4. Choose aspect ratio (optional) — select an output format or leave empty to match the source image.
5. Run — click the button to generate.
6. Download — preview and save your generated video.

Pricing

$0.28 per 5 seconds of output video.

Best Use Cases

• Fashion & Lookbooks — Animate model shots with realistic fabric movement and poses.
• Product Showcases — Bring product images to life with subtle motion and dynamic angles.
• Social Media Content — Create eye-catching video content from existing photos.
• Art & Illustration — Add movement to artwork, illustrations, and concept art.
• Marketing & Ads — Transform static campaign images into engaging video ads.

Example Prompts

• “A model walks forward slowly, the sculptural gown catching the light as fabric flows gracefully”
• “Camera slowly zooms in as soft wind moves through the hair”
• “The subject turns their head to look at the camera with a subtle smile”
• “Gentle camera pan to the right, revealing more of the scene”
• “Leaves fall softly in the background while the subject remains still”

Pro Tips for Best Results

• Be specific about motion — describe what moves, how it moves, and the camera behavior.
• Use the Prompt Enhancer to add cinematic details to simple descriptions.
• High-quality source images with clear subjects produce the best animations.
• Describe both subject motion and camera movement for more dynamic results.
• Keep prompts focused — one clear action often works better than multiple complex movements.
• Match aspect ratio to your intended platform: 9:16 for TikTok/Reels, 16:9 for YouTube.

Notes

• If using a URL for the image, ensure it is publicly accessible. A preview thumbnail confirms successful loading.
• Generation time may vary based on current queue load.
• Complex motions or detailed prompts may require iteration to achieve desired results.

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": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "duration": 5,
  "aspect_ratio": "16:9"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/runwayml/gen4-turbo" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 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) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters