Wan 2.5

Overview

Wan 2.5 (by Alibaba) is a cost-effective video model with good motion quality, especially for character animation. It supports text-to-video, image-to-video, and optional audio input.

Model ID	Quality	Credits	~Cost
`wan-2.5`	Standard	80	$0.80
`wan-2.5-preview`	Preview	60	$0.60

Quick start

import { createVarg } from "vargai/ai"

const varg = createVarg({ apiKey: process.env.VARG_API_KEY! })

const result = await varg.videoModel("wan-2.5").generate({
  prompt: "a cartoon character dancing energetically in a colorful studio",
  duration: 5,
  aspectRatio: "16:9",
})

console.log(result.video.url)

curl -X POST https://api.varg.ai/v2/video \
  -H "Authorization: Bearer $VARG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan-2.5",
    "prompt": "a cartoon character dancing energetically in a colorful studio",
    "duration": 5,
    "aspect_ratio": "16:9"
  }'

Capabilities

Text-to-video

const result = await varg.videoModel("wan-2.5").generate({
  prompt: "a woman walking through a busy market, vibrant colors, cinematic",
  duration: 8,
})

Image-to-video

cURL

curl -X POST https://api.varg.ai/v2/video \
  -H "Authorization: Bearer $VARG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan-2.5",
    "prompt": "the character starts walking forward slowly",
    "duration": 5,
    "files": [{ "url": "https://example.com/character.jpg" }]
  }'

Parameters

string

required

Text description of the video to generate.

string

default:"5"

Video duration in seconds. Range: 3-10 seconds.

string

default:"16:9"

Output aspect ratio.

array

Array of { url: string } objects for image-to-video.

object

Pass-through options. Supports resolution (default "480p"), negative_prompt, and audio_url for audio-driven generation.

Pricing

Model	Credits	USD
`wan-2.5`	80	$0.80
`wan-2.5-preview`	60	$0.60

One of the most affordable video models available.

Tips

Best value for character animation. Wan handles human and cartoon motion well at a fraction of Kling/Seedance cost.
Preview variant is good for quick iteration at even lower cost.
Combine with Soul for consistent character generation — use Soul to create the character image, then Wan to animate.
Audio input can drive motion — provide an audio_url in provider options for music-driven animation.

Kling V3

Higher quality, more expensive. Best for hero content.

Minimax

Similar price point, different motion characteristics.

LTX

Even cheaper at 50 credits. Fastest generation.

Get Started

Models

SDK

Templates

MCP

AI Agents

Comparisons

Overview

Quick start

Capabilities

Text-to-video

Image-to-video

Parameters

Pricing

Tips

Kling V3

Minimax

LTX

​Overview

​Quick start

​Capabilities

​Text-to-video

​Image-to-video

​Parameters

​Pricing

​Tips

​Related models

Kling V3

Minimax

LTX

Overview

Quick start

Capabilities

Text-to-video

Image-to-video

Parameters

Pricing

Tips

Related models