Wan 2.2 Plus Text to Video overview
Wan 2.2 Plus Text to Video by Alibaba Cloud
Wan2.2 T2V API enables multimodal AI workflows with visual reasoning, image-language analysis, streaming output, and automation support.
Wan 2.2 Plus Text to Video specs
- Model ID
alibaba/wan2.2-t2v-plus- Developer
- Alibaba Cloud
- Input
- Text, Image
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
Alibaba's Wan2.2 is a state-of-the-art AI model designed for multi-modal understanding, especially integrating text and vision inputs. It supports large context processing with superior precision in text-to-vision tasks and complex reasoning.
Performance Metrics
Wan2.1 leads with an overall VBench score of 86.22%, excelling in dynamic motion, spatial relationships, color accuracy, and multi-object interaction. Training foundational video models demands vast compute power and large, high-quality datasets. Open access to these models reduces barriers, empowering more businesses to create tailored, high-quality visual content in a cost-effective way.
Key Capabilities
- Vision-Language Fusion: Excels in interpreting and generating responses combining image and text data.
- Advanced Reasoning: Strong in multi-step reasoning across modalities for analytics and complex understanding.
Comparison with Other Models
Vs. Gemini 2.5 Flash: Higher multi-modal accuracy (78.3% vs. 70.8% VQA-bench), better for integrated tasks.
Vs. OpenAI GPT-4 Vision: Larger context window (65K vs. 32K tokens text) supports longer conversations with images.
Vs. Qwen3-235B-A22B: Superior cross-modal retrieval precision (81.9% vs. ~78% estimated), optimized for large-scale vision-language workflows.
Limitations
Occasionally, videos may contain unwanted elements such as text artifacts or watermarks; using negative prompts can mitigate but does not fully eliminate these occurrences.
API Integration
Accessible via AI/ML API. Documentation: available here.
Use cases
- Multi-modal Analysis: Combining image and text data for enhanced comprehension.
- Visual Question Answering (VQA): Accurate and context-aware answers based on image-text inputs.
- Cross-modal Retrieval: Efficient matching and retrieval across vision and language domains.
- Business Intelligence: Complex data interpretation integrating visual content with textual analytics.
Wan 2.2 Plus Text to Video API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.1 | per generation |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Wan 2.2 Plus Text to Video vs other video models: prices
AI/ML API rates for 5 models, per generation.
| Model | Per generation |
|---|---|
 Wan 2.2 Plus Text to Video | $0.1 |
| Wan 2.2 Vace Depth | $0.05 |
| Wan 2.2 Plus Image to Video | $0.1 |
 Gemini Omni | $0.1014 |
 Kling V2.1 Pro Image-to-Video | $0.103 |
How to use the Wan 2.2 Plus Text to Video 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/wan2.2-t2v-plus",
"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/wan2.2-t2v-plus",
"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/wan2.2-t2v-plus",
"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 2.2 Plus Text to Video
Related articles
Wan 2.2 Plus Text to Video FAQ
What inputs and outputs does Wan 2.2 Plus Text to Video support?
Wan 2.2 Plus Text to Video takes text as input and returns video.
When was Wan 2.2 Plus Text to Video released?
Wan 2.2 Plus Text to Video became available on November 20, 2025.
How much does Wan 2.2 Plus Text to Video cost?
Wan 2.2 Plus Text to Video costs $0.1 per generation on AI/ML API, billed as you go with no subscription.
How is Wan 2.2 Plus Text to Video billed?
Wan 2.2 Plus Text to Video is billed per generation, a fixed charge per output rather than by prompt length.
Who created Wan 2.2 Plus Text to Video?
Wan 2.2 Plus Text to Video was built by Alibaba Cloud.
How do I call Wan 2.2 Plus Text to Video on AI/ML API?
Send a request to v2/generate/video/alibaba/generation with alibaba/wan2.2-t2v-plus as the model id.
Is Wan 2.2 Plus Text to Video available through a single API key?
Yes. Wan 2.2 Plus Text to Video is served through AI/ML API, so the same key and endpoint format used for other models applies.
What quality improvements does Wan 2.2 Plus Text-to-Video offer?
It generates high-quality videos from text prompts with improved stability and coherence.
What is the Wan 2.2 Plus Text to Video model ID?
Use alibaba/wan2.2-t2v-plus as the model parameter. Requests go to https://api.aimlapi.com/v2/video/generations with your AI/ML API key.