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.
| Resolutions | Free | Pro | Max |
|---|---|---|---|
| 1080p | 29,444 | 28,237 | 27,031 |
What it takes and gives
- Text
- Image
- 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
