Try Hailuo 2.3 text-to-video online, watch motion and physics results, compare fixed 6- and 10-second pricing, and call POST /v1/tasks.
Provider: MiniMax
Category: video generation
Endpoint: /v1/tasks
Status: Available
Cost: See live page pricing
MiniMax Hailuo 2.3 text-to-video: the standard tier with excellent motion physics, 6s/10s clips billed per video.
Pricing
Standard Usage
Let the model automatically refine your prompt for better results
Ready for generation
Configure your parameters and click "Run" to see the output here.
Public model preview
Four public API results focus on people, crowd motion, fluid detail, and physical continuity. Each includes a matching poster and copyable prompt.
A public API result for evaluating motion stability, physical detail, and camera continuity.
Prompt shown with this public preview
a kung fu master practicing forms in heavy rain, water droplets scattering in slow motion, smooth natural motion, stable cinematic camera movement, consistent lighting across frames, cinematic composition, dramatic directional lighting, rich cohesive color grade, ultra-detailed, premium commercial finish
A public API result for evaluating motion stability, physical detail, and camera continuity.
Prompt shown with this public preview
a herd of horses galloping through a shallow river, water splashing high, smooth natural motion, stable cinematic camera movement, consistent lighting across frames, cinematic composition, dramatic directional lighting, rich cohesive color grade, ultra-detailed, premium commercial finish
A public API result for evaluating motion stability, physical detail, and camera continuity.
Prompt shown with this public preview
a girl swinging high on a rope swing under an autumn tree, leaves swirling, smooth natural motion, stable cinematic camera movement, consistent lighting across frames, cinematic composition, dramatic directional lighting, rich cohesive color grade, ultra-detailed, premium commercial finish
A public API result for evaluating motion stability, physical detail, and camera continuity.
Prompt shown with this public preview
overhead shot of latte art being poured, milk swirls forming a leaf pattern, smooth natural motion, stable cinematic camera movement, consistent lighting across frames, cinematic composition, dramatic directional lighting, rich cohesive color grade, ultra-detailed, premium commercial finish
Choose by input method, output specifications, control surface, and budget.
Faster image animation
Use the faster production route when a source image should define the opening composition.
Start from an image
Animate a specific source composition instead of creating it from text.
Longer low-cost route
Compare 6–30 second output with 480p and 720p controls.
Hailuo 2.3 is a pure text-to-video route with fixed 6- and 10-second output tiers. Its compact contract is useful for testing people, action, fluids, and physical motion without managing resolution or aspect-ratio fields.
Prompt optimization is enabled by default. The standard route is billed per completed video rather than per generated second. hailuo-2.3/text-to-video
These specifications reflect the current HiAPI Hailuo 2.3 Text to Video request contract.
Start with the 6-second tier and prompt optimization, then move to 10 seconds only when the action needs more room.
Lead with subject and setting, then describe action, camera direction, and speed in time order. State no cuts for a continuous take.
Draft
6-second tier
Final
10-second tier
Validate subject motion and camera continuity with 6-second tier, then move to 10-second tier.
Check motion stability and subject consistency online, then create an asynchronous task with the same model ID: hailuo-2.3/text-to-video.
This is the minimum request for an asynchronous text-to-video task. Use the API docs for task retrieval, callbacks, errors, and the complete parameter contract.
curl -X POST "https://api.hiapi.ai/v1/tasks" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "hailuo-2.3/text-to-video",
"input": {
"prompt": "A dancer spins on a rain-soaked rooftop at dusk, stable cinematic camera, natural motion.",
"duration": "6",
"prompt_optimizer": true
}
}'No. This route accepts a text prompt only. Use a separate Hailuo image-to-video model for a source frame.
The standard route offers fixed 6- and 10-second output tiers and does not expose resolution or aspect-ratio fields.
It is enabled by default to expand and organize the prompt. Turn it off when the original instruction must be preserved exactly.
It uses fixed per-video prices for the 6- and 10-second tiers.
POST an asynchronous task to /v1/tasks with model set to hailuo-2.3/text-to-video and pass prompt, duration, and prompt_optimizer inside input.
HiAPI Blog
