Wan 2.5 Text-to-Video Preview overview
Wan 2.5 Text-to-Video Preview by Alibaba Cloud
Wan 2.5 stands out with its strong prompt adherence and flexibility across various visual styles, delivering immersive and emotionally rich video content.
Wan 2.5 Text-to-Video Preview specs
- Model ID
alibaba/wan2.5-t2v-preview- Developer
- Alibaba Cloud
- Input
- Text
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
Wan 2.5 is an advanced AI model for generating high-quality, photorealistic videos directly from text prompts with synchronized audio. It represents a major leap in video generation technology, featuring native 4K support, cinematic controls, and natural motion synthesis. Designed for creators seeking professional-grade storytelling and emotional fidelity, Wan 2.5 delivers immersive, multi-minute video clips with fluid motion and precise audio-visual synchronization.
Technical Specifications
- Frame Rate: Typically 24 fps cinematic standard.
- Video Length: Generates videos up to several minutes long for continuous storytelling.
- Audio Support: Full audio integration allowing original sound input with precise lip-sync.
- Camera Controls: Pan, tilt, zoom, dolly, and rack focus for dynamic scene composition.
- Physics Engine: Advanced simulation for realistic motion and interaction effects.
Performance Benchmarks
- Video Quality: Produces ultra-detailed, photorealistic videos with rich environmental and facial details.
- Motion Smoothness: Superior motion stability with smooth transitions across both large and subtle movements.
- Audio-Visual Sync: Robust one-pass synchronization of video with uploaded voice or sound effects, surpassing competitors like Google Veo 3.
- Multilingual Performance: High accuracy lip-sync and voice matching across languages and accented speech.
- Cost Efficiency: More budget-friendly in computational cost compared to similar high-end models in the market.
Key Features
- Text-to-Video Generation: Create videos from detailed text descriptions.
- Native 4K Resolution Support: Produces ultra-high-definition video up to 4K quality.
- One-Pass Audio and Video Synchronization: Integrates voice, sound effects, and background music naturally aligned with visuals.
- Multilingual and Accent-Friendly: Supports multiple languages including Chinese and various accents with reliable lip-sync.
- Advanced Cinematic Controls: Fine control over camera movements (pan, tilt, zoom, dolly, rack focus) and lighting setups.
- Realistic Character & Motion Modeling: Near-photorealistic faces, nuanced expressions, natural body language, and interactions.
- Enhanced Physics Simulation: Realistic environmental interactions and smooth motion dynamics.
Use Cases
- Filmmaking and cinematic production with AI
- Advertising and marketing video generation
- Storyboarding and pre-visualization
- Social media content creation with audio-visual synchronization
- Multilingual video content for global audiences
- Character-driven narrative video with expressive emotions
Comparison with Other Models
vs Google Veo 3: Wan 2.5 supports native 4K video, longer clips, multilingual audio-visual synchronization including Chinese, and dynamic cinematic camera controls, while Veo 3 is limited to 1080p, shorter clips, English-centric audio sync, and basic fixed shots. Wan 2.5 is also more cost-efficient for creators with full audio input support versus Veo 3's system-generated sound only.
vs Runway Gen-4: Wan 2.5 excels in efficient real-time audio-video sync and native 4K output, offering enhanced motion fidelity and flexible camera workflows, whereas Runway Gen-4 focuses more on post-production effects and in-browser editing features but lacks deeper audio integration.
vs Pika Labs: Wan 2.5 generates longer continuous narrative videos with fine-tuned cinematic controls and multilingual voice syncing, compared to Pika Labs which provides faster short clip generation mainly for social media formats without advanced camera or audio sync features.
vs Kling 2.5 Turbo: Wan 2.5 offers superior photorealistic character rendering and precise lip-sync across languages, plus multiple video size outputs, while Kling 2.5 Turbo is optimized for high-speed generation and stylized animation effects but with less audio-visual integration.
API Integration
Accessible via AI/ML API. Documentation: available here.
Use cases
- Filmmaking and cinematic production with AI
- Advertising and marketing video generation
- Storyboarding and pre-visualization
- Social media content creation with audio-visual synchronization
- Multilingual video content for global audiences
- Character-driven narrative video with expressive emotions
Wan 2.5 Text-to-Video Preview API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.05 | per second |
The final price depends on request parameters such as resolution or duration.
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Wan 2.5 Text-to-Video Preview vs other video models: prices
AI/ML API rates for 5 models, per second.
| Model | Per second |
|---|---|
 Wan 2.5 Text-to-Video Preview | $0.05 |
| Wan 3.0 Video | $0.05 |
| Wan 2.7 Image to Video | $0.1 |
| Wan 2.7 Reference to Video | $0.1 |
| Happy Horse 1.1 | $0.14 |
How to use the Wan 2.5 Text-to-Video Preview API
View docs
Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v2/video/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "alibaba/wan2.5-t2v-preview",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "alibaba/wan2.5-t2v-preview",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}
response = requests.post("https://api.aimlapi.com/v2/video/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v2/video/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "alibaba/wan2.5-t2v-preview",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());The request returns a generation id. Poll GET https://api.aimlapi.com/v2/video/generations?generation_id=<id> until the status is completed.
Models similar to Wan 2.5 Text-to-Video Preview
Related articles
Wan 2.5 Text-to-Video Preview FAQ
What inputs and outputs does Wan 2.5 Text-to-Video Preview support?
Wan 2.5 Text-to-Video Preview takes text as input and returns video.
When was Wan 2.5 Text-to-Video Preview released?
Wan 2.5 Text-to-Video Preview became available on November 20, 2025.
How much does Wan 2.5 Text-to-Video Preview cost?
Wan 2.5 Text-to-Video Preview costs $0.05 per second on AI/ML API, billed as you go with no subscription.
How is Wan 2.5 Text-to-Video Preview billed?
Wan 2.5 Text-to-Video Preview costs $0.05 per second on AI/ML API, billed as you go with no subscription.
Who created Wan 2.5 Text-to-Video Preview?
Wan 2.5 Text-to-Video Preview was built by Alibaba Cloud.
How do I call Wan 2.5 Text-to-Video Preview on AI/ML API?
Send a request to v2/video/generations with alibaba/wan2.5-t2v-preview as the model id.
Is Wan 2.5 Text-to-Video Preview available through a single API key?
Yes. Wan 2.5 Text-to-Video Preview is served through AI/ML API, so the same key and endpoint format used for other models applies.
What video resolutions does Wan 2.5 Text-to-Video Preview support?
It can generate video in 480p, 720p, and 1080p resolutions.
What is the Wan 2.5 Text-to-Video Preview model ID?
Use alibaba/wan2.5-t2v-preview as the model parameter. Requests go to https://api.aimlapi.com/v2/video/generations with your AI/ML API key.