Hailuo 02 Standard

minimax /

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.

image-to-video

輸入

Enable Safety Checker

就緒

$0.23每次運行·~43 / $10

下一步：

示例查看全部

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.

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.

提示：本網站部分功能由第三方 AI 模型提供支援。

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. 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 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/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": false
}'

# 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/standard", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "duration": 6,
        "enable_prompt_expansion": false
}, {
    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/standard",
        {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "duration": 6,
    "enable_prompt_expansion": false
},
        timeout=3600.0,
        poll_interval=2.0,
    )
    print(output["outputs"])
except Exception as error:
    raise SystemExit(f"Generation failed: {error}") from error

Hailuo 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 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-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.