Hailuo
Text and image-to-video at native 1080p with accurate physics simulation and motion.
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/hailuo -gInstall the Hailuo skill for me: 1. Clone https://github.com/runapi-ai/hailuo 2. Copy the skills/hailuo/ directory into your user-level skills directory (e.g. ~/.claude/skills/ for Claude Code, ~/.codex/skills/ for Codex). 3. Verify that SKILL.md is present. 4. Confirm the install path when done.
Hailuo is MiniMax's video generation model capable of producing native 1080p footage with realistic physics simulation. It supports both text-to-video and image-to-video generation in standard and pro quality tiers.
- Installable agent skill
- Unified API key
- SDK examples included
- 실패한 생성은 과금되지 않습니다
변형
| Variant | Billing | From | |
|---|---|---|---|
| hailuo-02-image-to-video-pro | call | $0.570 | 보기 → |
| hailuo-02-image-to-video-standard | call | $0.300 | 보기 → |
| hailuo-02-text-to-video-pro | call | $0.570 | 보기 → |
| hailuo-02-text-to-video-standard | call | $0.500 | 보기 → |
| hailuo-2.3-image-to-video-pro | call | $0.900 | 보기 → |
| hailuo-2.3-image-to-video-standard | call | $0.500 | 보기 → |
Use this model from your agent
# User prompt to the agent
"Generate a 5-second clip of a glass marble rolling across a wooden desk and falling off the edge."// Code generated by the agent via @runapi.ai/hailuo
import { HailuoClient } from '@runapi.ai/hailuo';
const client = new HailuoClient();
const result = await client.imageToVideo.run({
model: 'hailuo-02-image-to-video-pro',
prompt: 'Generate a 5-second clip of a glass marble rolling across a wooden desk and falling off the edge.',
});How to call this model
Install the skill
Add the model skill to your agent or install the SDK package.
Authenticate once
Use your RunAPI key for every supported model.
Send a request
Use the unified schema for the endpoint you need.
Receive output
Poll by task ID or handle the callback when the generation completes.
SDK quickstart
curl -X POST https://runapi.ai/api/v1/hailuo/image_to_video \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "hailuo-02-image-to-video-pro",
"image_url": "https://cdn.runapi.ai/public/samples/image.jpg",
"prompt": "Generate a 5-second clip of a glass marble rolling across a wooden desk and falling off the edge."
}'import { HailuoClient } from "@runapi.ai/hailuo";
const client = new HailuoClient();
const result = await client.imageToVideo.run({
model: "hailuo-02-image-to-video-pro",
image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
prompt: "Generate a 5-second clip of a glass marble rolling across a wooden desk and falling off the edge.",
});require "runapi/hailuo"
client = RunApi::Hailuo::Client.new
result = client.image_to_video.run(
model: "hailuo-02-image-to-video-pro",
image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
prompt: "Generate a 5-second clip of a glass marble rolling across a wooden desk and falling off the edge."
)Where Hailuo fits
Hailuo is MiniMax's video model, known for accurate physics and motion fidelity at native 1080p. Through RunAPI, standard and pro variants share a single key.
Why use Hailuo through RunAPI
One API key
Use the same credentials across models and providers.
Agent-ready
Installable skills include docs and schema for tool calls.
Predictable billing
Usage-based pricing is visible before you call.
Frequently asked questions
How do I call this model?
Use the RunAPI SDK, CLI, or REST endpoint shown on this page.
Do failed generations cost money?
실패한 생성은 과금되지 않습니다
Can agents use it directly?
Yes. Install the model skill and your agent gets the docs, schema, and examples.
