Minimax H3 Video Extend API Documentation

Minimax H3 Video Extend API Documentation

Playground

MiniMax H3 Open Weights Video-Extend appends a new cinematic continuation to an existing video. A fresh segment with native stereo audio is generated from the input video’s last frame and a natural-language prompt, then the original and new segment are concatenated into a single output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

MiniMax H3 Video Extend Open Weights extends an existing video by generating a new segment from the input video’s last frame. The new segment is appended to the original video, with prompt-guided motion, scene continuation, and native audio generation.

Why Choose This?

• Video extension workflow
  Continue an existing video with a newly generated segment.

• Last-frame continuation
  Generate the new segment from the final frame of the input video for smoother visual continuity.

• Prompt-guided motion
  Describe the continuation, including action, camera movement, scene development, and soundtrack direction.

• Optional last-frame target
  Use last_image to guide where the extended segment should end.

• Native audio generation
  Generate audio together with the new video segment.

• Flexible resolution options
  Choose 480p for faster, lower-cost generation, 540p for a mid-price step up, 768p for the model’s native canvas, or 1080p for full-HD output.

Parameters

How to Use

1. Write the continuation prompt — Describe what should happen after the input video ends, including motion, scene, camera movement, and audio direction.
2. Upload the input video — Provide the video you want to extend.
3. Add last-frame guidance optional — Use last_image when you want to guide the final frame of the new segment.
4. Choose resolution — Use 480p for faster generation, 540p for a mid-price step up, 768p for the native canvas, or 1080p for full-HD output.
5. Set duration — Choose a new segment length from 3 to 15 seconds.
6. Set seed optional — Use a fixed seed for reproducible results, or a negative value for random generation.
7. Submit — Generate the extended video output.

Pricing

Pricing is based on the generated extension duration and selected resolution.

Duration is capped at 15 seconds for pricing.

Example Costs

video, last_image, prompt, and seed do not add separate charges.

Best Use Cases

• Video continuation — Extend an existing clip with a coherent new segment.
• Scene development — Continue action, camera movement, mood, and visual direction from the source video.
• Story extension — Add a new beat or ending to an existing short video.
• Start-to-target transitions — Use last_image when the extension needs to end on a specific visual state.
• Creative prototyping — Test different continuation prompts from the same source video.
• Social video content — Extend short clips for posts, reels, shorts, and creative previews.

Pro Tips

• Describe what should happen next instead of restating the full source video.
• Use a source video with a clear final frame for smoother continuation.
• Include camera movement, subject action, scene changes, mood, and audio cues in the prompt.
• Use last_image when the final pose, framing, or ending state matters.
• Keep the continuation focused on one clear event or motion direction.
• Use 480p for quick testing, 540p for a step up, and 768p or 1080p for higher-resolution output.
• Set a fixed seed when comparing prompt or parameter changes.

Notes

• prompt and video are required.
• duration supports values from 3 to 15 seconds.
• The new segment is generated from the input video’s last frame and appended to the original video.
• last_image is optional and guides the target ending frame of the new segment.
• Native audio is generated together with the extended segment.
• Pricing is based on the generated extension duration, not the input video duration.

Related Models

• MiniMax H3 Text-to-Video Open Weights — Generate video with native stereo audio directly from a text prompt.
• MiniMax H3 Image-to-Video Open Weights — Animate a first-frame image with prompt-guided motion and audio.
• MiniMax H3 Reference-to-Video Open Weights — Generate video from image, video, or audio references with prompt guidance.
• MiniMax H3 Video Edit Open Weights — Edit an existing video with prompt instructions and optional references.

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",
  "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
  "resolution": "480p",
  "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3/video-extend" \
  -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