Video · Alibaba

Wan API

Comprehensive video and image suite — text-to-video, image-to-video, video editing, and storyboards.

可正常運作 · 18 variants · 由 $0.050
runapi.ai
curl -X POST https://runapi.ai/api/v1/wan/image_to_video \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan-2.7-text-to-video",
  "image_url": "https://cdn.runapi.ai/public/samples/image.jpg",
  "prompt": "Generate a 5-second video of a cat jumping onto a bookshelf, natural indoor lighting, handheld camera feel."
}'
import { WanClient } from "@runapi.ai/wan";

const client = new WanClient();
const result = await client.imageToVideo.run({
    model: "wan-2.7-text-to-video",
    image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
    prompt: "Generate a 5-second video of a cat jumping onto a bookshelf, natural indoor lighting, handheld camera feel.",
});
<?php

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

use RunApi\Wan\WanClient;

$client = new WanClient();
$result = $client->imageToVideo->run([
        'model' => 'wan-2.7-text-to-video',
        'image_url' => 'https://cdn.runapi.ai/public/samples/image.jpg',
        'prompt' => 'Generate a 5-second video of a cat jumping onto a bookshelf, natural indoor lighting, handheld camera feel.',
]);
require "runapi/wan"

client = RunApi::Wan::Client.new
result = client.image_to_video.run(
    model: "wan-2.7-text-to-video",
    image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
    prompt: "Generate a 5-second video of a cat jumping onto a bookshelf, natural indoor lighting, handheld camera feel."
)
npx skills add runapi-ai/wan -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/wan v1
OVERVIEW

Wan is Alibaba's comprehensive video and image generation suite covering text-to-video, image-to-video, video editing, speech-to-video, and storyboard generation. It spans multiple model versions optimized for quality, speed, and specialized creative tasks.

  • 多個變體,對應不同速度/品質層級
  • Model skill 包含文件、schema 與 setup 備註
  • 支援 app-focused coding workflows
  • 生成失敗不收費
VARIANTS

比較所有 API 變體

Variant Billing From
wan-2.2-a14b-image-to-video-turbo call $0.400 查看 →
wan-2.2-a14b-speech-to-video-turbo second $0.240 查看 →
wan-2.2-a14b-text-to-video-turbo call $0.400 查看 →
wan-2.2-animate-move second $0.130 查看 →
wan-2.2-animate-replace second $0.130 查看 →
wan-2.5-image-to-video second $0.120 查看 →
wan-2.5-text-to-video second $0.120 查看 →
wan-2.6-edit-video second $0.140 查看 →
wan-2.6-flash-edit-video call $0.300 查看 →
wan-2.6-flash-image-to-video call $0.300 查看 →
wan-2.6-image-to-video second $0.140 查看 →
wan-2.6-text-to-video second $0.140 查看 →
wan-2.7-edit-video second $0.160 查看 →
wan-2.7-image call $0.050 查看 →
wan-2.7-image-pro call $0.120 查看 →
wan-2.7-image-to-video second $0.160 查看 →
wan-2.7-r2v second $0.160 查看 →
wan-2.7-text-to-video second $0.160 查看 →
SKILLS

為 app 開發安裝 Wan skill

將模型文件、schema、價格備註與 setup 步驟載入 coding workspace。

# Install the model skill for app development workflows
npx skills add runapi-ai/wan -g
Installs docs, schemas, pricing context, and setup notes into your developer workspace.
Or use this setup request in your coding tool:
Install the Wan skill for this app:

1. Add runapi-ai/wan with the skills installer.
2. Load SKILL.md in this workspace.
3. Use its docs, schemas, pricing notes, and setup steps when adding model features.
4. Confirm the install path when done.
運作方式

從 model skill 到第一次結果,只需四步

01

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。

02

設定

設定 RunAPI key,並在 coding workspace 安裝 model skill。

03

開發

使用 skill 指引,在你的 app 內加入模型功能。

04

接收

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

CONTEXT

Wan API 是甚麼?

Wan is Alibaba's full-spectrum video and image model suite, one of the most complete open-weight video families available. Through RunAPI, all Wan versions share a single key and unified billing.

Provider
Alibaba
Modality
Video
點解揀 RunAPI

為何透過 RunAPI 使用 Wan 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。

FAQ

常見問題

How many Wan versions are available?

Versions 2.2, 2.5, 2.6, and 2.7, each adding new capabilities. 2.7 is the latest with first-and-last-frame control and multi-reference video generation.

What is speech-to-video?

The speech-to-video endpoint on Wan 2.2 takes audio input and generates video with lip-synced motion driven by the speech content.

Does Wan support video editing?

Yes — Wan 2.6+ includes video editing and Wan 2.7 adds a dedicated video editing endpoint with subject and camera control.

Is Wan open source?

Partly — Wan 2.1 and 2.2 are released as open weights under the Apache 2.0 license. The later versions (2.5, 2.6, and 2.7) are closed, API-only models.

What is the R2V endpoint?

Wan 2.7 R2V uses the text-to-video endpoint with reference image, video, and audio inputs to anchor a character's appearance and voice across clips.

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。

有免費方案嗎?

新帳戶可獲得每個模型的首次呼叫免費。之後按次收費。

你哋支援串流結果嗎?

如有提供串流,RunAPI 會端到端串流。

失敗會點樣收費?

生成失敗不會收費。

輸出有快取嗎?

已生成輸出會儲存,並可按任務 ID 取回。輸入內容不會快取。

可以商業使用嗎?

可以——除非模型授權明確限制,否則每個版本都包括商業使用。相關限制會在版本頁面列明。

限流點樣計?

每個密鑰的限流會跟使用等級而提升。最新限制請參考定價頁。

可以在邊度報告問題?

可以在公開 GitHub repo 開 issue,或者電郵支援。

立即開始

開始用 Wan API 開發。