It looks like you may prefer a different language. Switch anytime.

Video MiniMax

Hailuo API

透過 RunAPI 使用 Hailuo API,包含 model skill、統一驗證與按用量計費。

runapi.ai
curl -X POST https://runapi.ai/api/v1/hailuo/image_to_video \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "hailuo-2.3-image-to-video-standard",
  "image_url": "https://cdn.runapi.ai/public/samples/image.jpg",
  "prompt": "Generate a 6-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-2.3-image-to-video-standard",
    image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
    prompt: "Generate a 6-second clip of a glass marble rolling across a wooden desk and falling off the edge.",
});
<?php

require __DIR__ . "/vendor/autoload.php";

use RunApi\Hailuo\HailuoClient;

$client = new HailuoClient();
$result = $client->imageToVideo->run([
        'model' => 'hailuo-2.3-image-to-video-standard',
        'image_url' => 'https://cdn.runapi.ai/public/samples/image.jpg',
        'prompt' => 'Generate a 6-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-2.3-image-to-video-standard",
    image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
    prompt: "Generate a 6-second clip of a glass marble rolling across a wooden desk and falling off the edge."
)
npx skills add runapi-ai/hailuo -g
# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp

# Codex
codex plugin install runapi-mcp@agents

# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursor
@runapi.ai/hailuo v1
OVERVIEW

關於 Hailuo

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.

供應商
MiniMax
模式
Video

比較所有 API 變體

變體 計費 定價
hailuo-02-image-to-video-pro call $0.570 查看 →
hailuo-02-image-to-video-standard call $0.500 查看 →
hailuo-02-text-to-video-pro call $0.570 查看 →
hailuo-02-text-to-video-standard call $0.500 查看 →
hailuo-2.3-image-to-video-pro call $0.900 查看 →
hailuo-2.3-image-to-video-standard call $0.500 查看 →
PRICING

Hailuo 定價

Endpoint 解析度 時長 價格
image_to_video $0.57 / video

以下為 hailuo-02-image-to-video-pro 的定價。其他變體保留各自的 endpoint 定價。

Agent 整合

透過 Agent 執行 Hailuo

運作方式

開始使用 Hailuo

  1. 選擇模型

    挑選符合輸出類型、品質門檻與延遲目標的模型與變體。

  2. 設定

    設定 RunAPI key,並在 coding workspace 安裝 model skill。

  3. 開發

    使用 skill 指引,在你的 app 內加入模型功能。

  4. 接收

    透過 task ID 查詢、在支援時串流,或處理 webhook callback。

CONTEXT

Hailuo API 是甚麼?

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.

供應商
MiniMax
查看全部 →
模式
Video
瀏覽模型 →

為何透過 RunAPI 使用 Hailuo API

一個驗證,對應所有 provider

一組 RunAPI key 即可解鎖整個 catalog。無需分開帳戶,亦無需為每個整合輪換密鑰。

統一定價與計費

按次以 USD 收費,每月結算。失敗的生成不會收費。

內含 schema 的 skill

型別化 schema 與 setup 備註打包在 model skill 內,讓實作從正確契約開始。

Hailuo 常見問題

What resolution does Hailuo output?

Pro 變體原生 1080p。Standard 變體最高輸出 768p,其中 Hailuo 2.3 standard 可達 1080p。Pro 層級毋須後期放大。

How long are generated clips?

Up to 10 seconds per generation for both text-to-video and image-to-video endpoints.

How realistic is the physics simulation?

Hailuo is specifically trained for accurate physics — fluid dynamics, object collisions, gravity, and cloth movement render with high fidelity.

What is the difference between standard and pro?

Pro 原生輸出 1080p,細節同動態保真度更佳。Standard 最高輸出 768p(Hailuo 2.3 standard 可達 1080p),費用約平 50%。

Does Hailuo 2.3 improve over 02?

Yes — 2.3 adds improved body motion, micro-expressions, and dedicated anime/illustration styles not available in the 02 generation.

我應該先用邊個版本?

先選最平而且符合你質素要求的版本。大多數團隊會先用快速版本,之後再升級到 pro 用於正式生產。

相似模型

如果你鍾意 Hailuo API,可以試吓呢些

開始用 Hailuo API 開發。