Hailuo 2.3
Vendor: MiniMax
Cinematic quality with fast generation speed
- Typical latency
- 30-90s
- Reference inputs
- Up to 1
- toolId
- hailuo-2-3
Input modes
Variants
Standard Text to Video
Standard Hailuo 2.3 text-to-video generation
Standard Image to Video
Animate one source image with Hailuo 2.3 Standard
Pro Text to Video
Higher-quality Hailuo 2.3 text-to-video generation
Pro Image to Video
Higher-quality Hailuo 2.3 image animation
Fast Standard Image to Video
Faster Hailuo 2.3 Standard image animation
Fast Pro Image to Video
Faster Hailuo 2.3 Pro image animation
Parameters
| Parameter | Type | Default | Values | Notes |
|---|---|---|---|---|
| duration | select | 6 | 6 | 10 | Clip length. Longer clips cost more; re-quote after changing. |
| prompt_optimizer | toggle | true | — | Automatically enhance your prompt for better results |
Pricing
Pricing will be published shortly — contact us for early access rates
Prices last updated: —
API example
curl -X POST https://api.mukelabs.com/v1/generations \
-H "Authorization: Bearer $MUKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"toolId": "hailuo-2-3",
"inputMode": "text-to-video",
"prompt": "your prompt here",
"params": { "duration": "6" },
"references": [],
"idempotencyKey": "a-unique-key-per-task",
"subjectId": "your-user-id"
}'FAQ
How do I call Hailuo 2.3 on Muke Labs?
What does Hailuo 2.3 cost?
What happens if a task fails?
Where do I get an API key?
Related models
MiniMax H3
MiniMax
Create high-detail videos from text, or from image, video, and audio references
Auto Video Watermark Remover
Alibaba
Remove logos, captions, and watermarks from a video without drawing a mask
Digital Human - HeyGen
HeyGen
Generate or lip-sync avatar videos from media plus uploaded speech audio
Digital Human - InfiniTalk
InfiniTalk
Create talking-avatar videos from a portrait image plus voice audio