Minimax Video 01 API Documentation

Minimax Video 01 API Documentation

Playground

Minimax Video-01 is a text-to-video model offering high compression, strong text responsiveness, cinematic styles, and native HD output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

MiniMax Video-01 is a text-to-video (T2V) model for generating short, coherent clips from a single prompt. It’s built for cinematic pacing, stable scene continuity, and prompt-faithful motion, making it a strong default for story beats, product shots, and concept trailers.

What it’s good at

• Text-to-Video (T2V): generate a complete clip from a prompt
• Cinematic language: responds well to shot descriptions and camera cues
• Coherent motion: maintains continuity across frames for simple-to-moderate action
• Fast iteration: great for rapid creative exploration and storyboard-style outputs

Inputs

• Prompt (required): describe subject, action, environment, lighting, camera, and style
• Image (optional, if supported in your deployment): provide a reference frame to steer the look
• Enable prompt expansion (optional): automatically expands/optimizes your prompt for better visual quality

Key parameters

• enable_prompt_expansion:

• On: better visual richness and fewer “under-specified” results

• Off: tighter control, closer to your exact wording (often best for structured prompts)

Prompting tips

• Use a “director brief” structure:

• Subject: who/what is on screen

• Action: what changes over time

• Scene: where + time of day + lighting

• Camera: framing + movement + transitions

• Style: mood + medium + references (optional)

• Prefer one clear main action per clip (then iterate).

• If you need stronger motion, add pace and intent: slowly, rapidly, abrupt cut, smooth dolly-in, handheld shake.

Use cases

• Concept trailers & story beats: quick visual drafts for narrative sequences
• Marketing clips: product mood videos and brand-style visuals
• Social content: punchy short clips with strong camera direction
• Pre-visualization: test shots, lighting, and staging before production

Pricing

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",
  "enable_prompt_expansion": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/minimax/video-01" \
  -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