Hailuo 02 T2V Standard

minimax /

Hailuo 02 is a text-to-video model on MiniMax, fine-tuned to output responsive 768P videos even for complex physics-driven scenes. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-video

입력

Enable Safety Checker

대기 중

$0.23실행당·~43 / $10

예시전체 보기

A stylish couple dancing a slow tango in a dimly lit room, passionate glances, moody lighting, sultry music, sensual rhythm

A confident woman walking alone through an upscale lounge bar, wearing a black slit gown, subtle flirtatious expressions, cinematic camera sweep

A mysterious woman in a sheer dress walking through a moonlit hallway, slow camera pan, flirtatious expressions, high heels echoing, glowing ambient lighting, soft focus

A realistic video of a young man walking down a busy city street, sunlight reflecting on glass buildings, natural footsteps, slight camera shake, people passing by, realistic lighting and shadows, the man glances around casually and adjusts his jacket, cinematic urban atmosphere

a realistic video of a woman sitting by the window in a coffee shop, typing on her laptop, soft natural light on her face, steam rising from a cup of coffee, shallow depth of field, gentle background motion, natural breathing and subtle head movements

README

Hailuo 02 — Text-to-Video (T2V Standard)

minimax/hailuo-02/t2v-standard converts pure text into cinematic video with strong prompt adherence, believable physics, and smooth scene transitions. Built on MiniMax’s evolving framework, it balances quality, speed, and cost for everyday creative production.

Why it works

768p output — crisp frames, ready for editing.
6s / 10s clips — fast ideation or trailer-style beats.
Enhanced motion & physics — debris, cloth, water, camera shake look natural.
Cinematic continuity — fewer artifacts; smoother temporal flow.
Repeatable — low randomness for the same prompts.

Limits & Performance

Resolution: 768p
Durations: 6s or 10s
Runtime: ~30–90 s per clip (scene complexity & queue dependent)

Pricing

Duration	Cost per job	Max Resolution
6 s	$0.23	768p
10 s	$0.56	768p

How to Use

Prompt — Describe scene, lighting, motion, and camera.
Duration — Choose 6s or 10s.
(Optional) Prompt expansion — Enable for smarter parsing & safety.
Run — Review, tweak prompt/seed, and iterate.

Pro Tips

Write like a director: shot type, camera move, lighting, mood.
Use action verbs: dolly in, orbit, rack focus, particles swirl.
Start with 6s for quick iterations; assemble multiple clips for longer stories.
Add your own music/VO for complete narratives.

참고:이 웹사이트는 제3자가 제공하는 AI 모델을 사용합니다.

Hailuo 02 T2v Standard API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/minimax/hailuo-02/t2v-standard with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read URLs from data.outputs. Examples for Hailuo 02 T2v Standard below.

HTTP example

# Submit the prediction
curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/minimax/hailuo-02/t2v-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",
    "duration": 6,
    "enable_prompt_expansion": true
}'

# Wait at least 2 seconds, then poll. Safe GET requests may be retried.
curl --fail-with-body --connect-timeout 10 --max-time 30 \
  --retry 4 --retry-all-errors --retry-delay 1 \
  -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# Start at 2 seconds and increase the interval for long-running tasks.
# Stop on completed, failed, cancelled, or timeout.

Node.js example

// npm install wavespeed
const { Client } = require('wavespeed');

const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
const client = new Client(apiKey);

try {
  const result = await client.run("minimax/hailuo-02/t2v-standard", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "duration": 6,
        "enable_prompt_expansion": true
}, {
    timeout: 3600,
    pollInterval: 2.0,
  });
  console.log(result.outputs);
} catch (error) {
  console.error('Generation failed:', error);
  process.exitCode = 1;
}

Python example

# pip install wavespeed
import os
from wavespeed import Client

client = Client(api_key=os.environ["WAVESPEED_API_KEY"])

try:
    output = client.run(
        "minimax/hailuo-02/t2v-standard",
        {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "duration": 6,
    "enable_prompt_expansion": true
},
        timeout=3600.0,
        poll_interval=2.0,
    )
    print(output["outputs"])
except Exception as error:
    raise SystemExit(f"Generation failed: {error}") from error

Hailuo 02 T2v Standard API — Frequently asked questions

What is the Hailuo 02 T2v Standard API?

Hailuo 02 T2v Standard is a MiniMax model for video generation, exposed as a REST API on WaveSpeedAI. Hailuo 02 is a text-to-video model on MiniMax, fine-tuned to output responsive 768P videos even for complex physics-driven 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 T2v 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 result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/minimax/minimax-hailuo-02-t2v-standard.

How much does Hailuo 02 T2v Standard cost per run?

Hailuo 02 T2v 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 T2v Standard accept?

Key inputs: `prompt`, `duration`, `enable_prompt_expansion`. 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-t2v-standard.

How long does Hailuo 02 T2v Standard take to generate?

Average end-to-end generation time on WaveSpeedAI is around 106 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 T2v 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.