Minimax H3 Lite Text To Video API Documentation

Minimax H3 Lite Text To Video API Documentation

Playground

MiniMax H3 Lite Text-to-Video generates 480P / 768P videos from text prompts with flexible 4-15 second duration, making it suitable for creative videos, social content, ads, marketing, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

MiniMax H3 Lite Text-to-Video generates videos directly from text prompts. Describe the scene, action, camera movement, and visual style, then choose a duration from 4 to 15 seconds, a resolution, and a supported aspect ratio.

Why Choose This?

• Text-to-video generation — Create videos directly from natural-language prompts.
• Flexible duration — Generate clips from 4 to 15 seconds.
• 480p and 768p output — Choose the resolution that fits your workflow.
• Multiple aspect ratios — Generate landscape, portrait, square, or ultrawide videos.
• Prompt-driven control — Describe subjects, actions, environments, camera movement, and visual style.

Parameters

How to Use

1. Write a prompt — Describe the subject, setting, action, camera movement, and visual style.
2. Choose duration — Select a video length from 4 to 15 seconds.
3. Choose resolution — Select 480p or 768p.
4. Choose framing — Select the aspect ratio that fits your target format.
5. Submit — Generate and retrieve the completed video.

Pricing

Pricing is based on the requested video duration and selected resolution.

Example Costs

Best Use Cases

• Cinematic concepts — Turn scene descriptions into short video clips.
• Social media content — Generate landscape, portrait, or square videos.
• Advertising concepts — Create promotional and campaign video ideas.
• Creative storytelling — Generate short narrative scenes from text.
• Visual prototyping — Explore camera movement, environments, and motion concepts.

Pro Tips

• Keep the main subject and action clear.
• Describe camera movement explicitly when it matters.
• Include lighting, environment, and visual style for stronger direction.
• Keep the requested action suitable for the selected duration.
• Use 480p for lower-cost iteration before moving to 768p.

Notes

• prompt is required.
• duration supports whole-second values from 4 to 15 and defaults to 5.
• resolution supports 480p and 768p and defaults to 768p.
• Supported aspect ratios are 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16. Default: 16:9.

Related Models

• MiniMax H3 Lite Image-to-Video — Generate videos from a starting image.
• MiniMax H3 Lite Reference-to-Video — Generate videos using image, video, and audio 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",
  "aspect_ratio": "16:9",
  "resolution": "768p",
  "duration": 5
}
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/minimax/h3-lite/text-to-video" \
  -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