Hailuo 02 is an AI video-generation model delivering 768P output with fast responsiveness and strong handling of complex physics scenes. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.23per run·~43 / $10
ExamplesView all
A kitten chases a bouncing rubber ball across a polished wooden floor, sliding slightly and bumping into a potted plant.
Soft spotlight hits a ballerina as she twirls gracefully on a dusty wooden stage, particles swirling around her feet.
A woman rides a hoverbike across a cracked desert highway, dust trailing behind her, while abandoned mechs lie rusting under the harsh sun.
A young elephant balances on a large rubber ball in a dusty circus ring, flapping its ears for balance as children cheer.
A golden retriever puppy runs across a bright green meadow filled with dandelions, ears flapping, sunlight bouncing off its fur in slow motion.
Related Models
README
minimax/hailuo-02/standard
Hailuo 02 Standard is the unified model on MiniMax’s framework. It generates cinematic clips with 768p clarity, strong prompt adherence, believable physics, and smooth temporal transitions. Use it as pure T2V (text only) or guided I2V (add a start image, optional end image for a planned transition).
Why creators like it
- One endpoint, two modes — Text-to-Video or Image-guided Video.
- Native 768p — crisp frames, not upscaled.
- 6s / 10s clips — quick iteration or trailer pacing.
- Physics & motion — debris, cloth, water, handheld shake look natural.
- Stable & repeatable — good consistency across re-runs.
Parameters
| Name | Description |
|---|---|
| prompt* | Describe scene, lighting, motion, and camera. |
| image | (Optional) Use a reference/first frame (JPG/PNG) to lock composition & style. |
| end_image | (Optional) Target frame for a guided transition. |
| duration | 6s or 10s. |
| enable_prompt_expansion | Auto-refines prompt and runs a safety check. |
Pricing
| Duration | Cost per job | Resolution |
|---|---|---|
| 6 s | $0.23 | 768p |
| 10 s | $0.56 | 768p |
How to use (short)
- Write a prompt (include camera + motion + lighting).
- (Optional) Add image (and end_image for a transition).
- Pick duration (6s/10s), keep prompt expansion on.
- Run → review → tweak prompt → re-run.
Example prompts
- A boy and his dog race along the beach at sunset; camera tracks low and wide, warm reflections on wet sand, gentle spray, cinematic grade.
- Slow orbit around a neon-lit street food stall in the rain; steam and bokeh, handheld vibe, rack focus to the chef’s hands.
Hailuo 02 Standard API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/minimax/hailuo-02/standard with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Hailuo 02 Standard below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/minimax/hailuo-02/standard" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"duration": 6,
"enable_prompt_expansion": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("minimax/hailuo-02/standard", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"duration": 6,
"enable_prompt_expansion": false
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"minimax/hailuo-02/standard",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"duration": 6,
"enable_prompt_expansion": false
}
)
print(output["outputs"][0]) # → URL of the generated outputHailuo 02 Standard API — Frequently asked questions
What is the Hailuo 02 Standard API?
Hailuo 02 Standard is a MiniMax model for video generation from images, exposed as a REST API on WaveSpeedAI. Hailuo 02 is an AI video-generation model delivering 768P output with fast responsiveness and strong handling of complex physics scenes. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Hailuo 02 Standard API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/minimax/minimax-hailuo-02-standard.
How much does Hailuo 02 Standard cost per run?
Hailuo 02 Standard starts at $0.23 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Hailuo 02 Standard accept?
Key inputs: `prompt`, `image`, `duration`, `enable_prompt_expansion`, `end_image`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/minimax/minimax-hailuo-02-standard.
How long does Hailuo 02 Standard take to generate?
Average end-to-end generation time on WaveSpeedAI is around 116 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Hailuo 02 Standard outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (MiniMax). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.