Wan
Comprehensive video and image suite — text-to-video, image-to-video, video editing, and storyboards.
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/wan -g
Install the Wan skill for me: 1. Clone https://github.com/runapi-ai/wan 2. Copy the skills/wan/ 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.
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.
- Installable agent skill
- Unified API key
- SDK examples included
- 실패한 생성은 과금되지 않습니다
변형
| Variant | Billing | From | |
|---|---|---|---|
| wan-2.2-a14b-image-to-video-turbo | call | $0.400 | 보기 → |
| wan-2.2-a14b-speech-to-video-turbo | second | $0.240 | 보기 → |
| wan-2.2-a14b-text-to-video-turbo | call | $0.400 | 보기 → |
| wan-2.2-animate-move | second | $0.130 | 보기 → |
| wan-2.2-animate-replace | second | $0.130 | 보기 → |
| wan-2.5-image-to-video | second | $0.120 | 보기 → |
| wan-2.5-text-to-video | second | $0.120 | 보기 → |
| wan-2.6-edit-video | second | $0.140 | 보기 → |
| wan-2.6-flash-edit-video | call | $0.300 | 보기 → |
| wan-2.6-flash-image-to-video | call | $0.300 | 보기 → |
| wan-2.6-image-to-video | second | $0.140 | 보기 → |
| wan-2.6-text-to-video | second | $0.140 | 보기 → |
| wan-2.7-edit-video | second | $0.160 | 보기 → |
| wan-2.7-image | call | $0.050 | 보기 → |
| wan-2.7-image-pro | call | $0.120 | 보기 → |
| wan-2.7-image-to-video | second | $0.160 | 보기 → |
| wan-2.7-r2v | second | $0.160 | 보기 → |
| wan-2.7-text-to-video | second | $0.160 | 보기 → |
Use this model from your agent
# User prompt to the agent
"Generate a 5-second video of a cat jumping onto a bookshelf, natural indoor lighting, handheld camera feel."
// Code generated by the agent via @runapi.ai/wan
import { WanClient } from '@runapi.ai/wan';
const client = new WanClient();
const result = await client.imageToVideo.run({
model: 'wan-2.2-a14b-image-to-video-turbo',
prompt: 'Generate a 5-second video of a cat jumping onto a bookshelf, natural indoor lighting, handheld camera feel.',
});
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/wan/image_to_video \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-2.2-a14b-image-to-video-turbo",
"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-2.2-a14b-image-to-video-turbo",
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-2.2-a14b-image-to-video-turbo",
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."
)
Where Wan fits
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.
Why use Wan 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.
Models similar to Wan
Start building with Wan.
- Wan wan-2.2-a14b-image-to-video-turbo
- Wan wan-2.2-a14b-speech-to-video-turbo
- Wan wan-2.2-a14b-text-to-video-turbo
- Wan wan-2.2-animate-move
- Wan wan-2.2-animate-replace
- Wan wan-2.5-image-to-video
- Wan wan-2.5-text-to-video
- Wan wan-2.6-edit-video
- Wan wan-2.6-flash-edit-video
- Wan wan-2.6-flash-image-to-video
- Wan wan-2.6-image-to-video
- Wan wan-2.6-text-to-video
- Wan wan-2.7-edit-video
- Wan wan-2.7-image
- Wan wan-2.7-image-pro
- Wan wan-2.7-image-to-video
- Wan wan-2.7-r2v
- Wan wan-2.7-text-to-video