Hailuo 02 Fast is a minimax image-to-video model that creates high-quality 6s and 10s clips at 512p for creators and marketers. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.1per run·~10 / $1
A top snowboarder launches off a massive kicker on a cliff's edge, executing a grab in mid-air. The backdrop is a clear blue sky and a vast mountain range. Powdered snow erupts behind him like smoke in the bright sunlight. Drone-following shot, capturing his perfect form in the air and his smooth landing from a side angle. Extreme sports, 4K, high frame rate, GoPro-like perspective.
A girl in a white tracksuit is jogging on a coastal road. The soft morning sun illuminates the side of her face as a bead of sweat rolls down her cheek. Waves rhythmically crash onto the beach in the background, with the horizon stretching out where the sea meets the sky. A side-tracking shot captures her light-footed stride and determined expression. Motion blur effect, inspirational mood, fresh colors.
In a dimly lit boxing ring, two boxers are intensely facing off. Their eyes are sharp, their bodies slightly swaying as they look for an opening. Sweat glistens on their foreheads. The camera rapidly switches between the two fighters, capturing the moments of their punches, dodges, and powerful expressions. Competitive, tense, a sense of power.
A surfer is riding inside the barrel of a massive, crystal-clear wave. The camera is positioned inside the tube, offering a breathtaking view of the water wall enveloping the surfer. Sunlight filters through the curtain of water, creating dreamlike light effects. Water splashes, the surfer's expression is focused and exhilarated. First-person view (FPV), wide-angle lens, underwater photography texture, realism.
A tranquil lake at sunset, a gentle breeze rustles the trees on the shore, the camera slowly pans across the water, the golden light reflects on the ripple, ultra realistic, cinematic, high detail.
Hailuo 02 Fast is the speed/throughput variant of the Hailuo 02 engine. It animates a single image into a smooth clip in 6s or 10s, with prompt-aware motion, strong physics, and a cost optimized for rapid iteration and batch A/B testing.
| Name | Description |
|---|---|
| image* | Starting frame (JPG/PNG). Required. |
| prompt | Optional scene/camera/motion description to guide animation. |
| duration | 6s or 10s. |
| enable_prompt_expansion | Auto-refines prompt + safety check. |
| go_fast | Prioritize speed with a moderate quality trade-off (recommended ON). |
| Duration | Cost per job |
|---|---|
| 6 s | $0.10 |
| 10 s | $0.15 |
A top snowboarder launches off a massive kicker on a cliff’s edge; drone follows, powdered snow billows in bright sunlight; fast shutter, cinematic grade.
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/minimax/hailuo-02/fast 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 Fast below.
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/minimax/hailuo-02/fast" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"image": "https://example.com/your-input.jpg",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 6,
"enable_prompt_expansion": true,
"go_fast": true
}'
# 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].// 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/fast", {
"image": "https://example.com/your-input.jpg",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 6,
"enable_prompt_expansion": true,
"go_fast": true
});
console.log(result.outputs[0]); // → URL of the generated output# pip install wavespeed
import wavespeed
output = wavespeed.run(
"minimax/hailuo-02/fast",
{
"image": "https://example.com/your-input.jpg",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 6,
"enable_prompt_expansion": true,
"go_fast": true
}
)
print(output["outputs"][0]) # → URL of the generated outputHailuo 02 Fast is a MiniMax model for video generation from images, exposed as a REST API on WaveSpeedAI. Hailuo 02 Fast is a minimax image-to-video model that creates high-quality 6s and 10s clips at 512p for creators and marketers. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
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-fast.
Hailuo 02 Fast starts at $0.10 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.
Key inputs: `prompt`, `image`, `duration`, `enable_prompt_expansion`, `go_fast`. 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-fast.
Average end-to-end generation time on WaveSpeedAI is around 72 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
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.