Skip to content
FluxCDNFluxCDN
esc

MiniMax: Hailuo 2.3

Hailuo 2.3 is a video generation model from MiniMax. It accepts text prompts and reference images as input and generates video output, supporting both text-to-video and image-to-video workflows.

From
29,444 Toman/second
Durations
6–10 s
Resolutions
1080p
Aspect ratios
16:9
Published
Apr 20, 2026
Maker
MiniMax

Free plan prices, in Toman at today's rate. Plans and prices

Price per second, by plan

Toman per second of video at today's rate, by resolution. A video is charged once, when it is ready, at the price frozen when it was submitted; nothing is charged if it fails.

ResolutionsFreeProMax
1080p29,44428,23727,031

What it takes and gives

Accepts
  • Text
  • Image
Creates
  • Video

Every input listed here works through the API and the playground: images and PDFs as data URLs or https links, audio as base64, video as a data URL or a link the model supports.

This model creates video. Send it to POST /v1/videos with a prompt (and optionally a first or last frame), poll the job until it is completed — usually 30 seconds to a few minutes — then download it. Nothing is charged if it fails.

Video options

Durations
6 s, 10 s
Resolutions
1080p
Aspect ratios
16:9
Start from an image
first frame
Sound
silent

Call it

curl https://ai.fluxcdn.cloud/api/v1/videos \
  -H "Authorization: Bearer $FLUXCDN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/hailuo-2.3",
    "prompt": "A slow aerial shot over Mount Damavand at sunrise",
    "duration": 6,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }'

→ 202 {"id": "vid_…", "status": "pending", "polling_url": "…/api/v1/videos/vid_…"}

curl https://ai.fluxcdn.cloud/api/v1/videos/vid_… -H "Authorization: Bearer $FLUXCDN_API_KEY"
→ {"status": "completed", "content_urls": ["…/api/v1/videos/vid_…/content?index=0"], "cost_micros": …}

curl -L https://ai.fluxcdn.cloud/api/v1/videos/vid_…/content -H "Authorization: Bearer $FLUXCDN_API_KEY" -o video.mp4