All models

wan-video-2.1 Video Generation by Alibaba / Wan Team High-quality video from text or image. Smooth motion. Cinematic output.

Up to 1280×720 ~45s generation From $0.15/video 5s clips
View API docs →

Specifications

Model ID

wan-video-2.1

Provider

Alibaba / Wan Team

Modality

Video Generation (text-to-video, image-to-video)

Max Resolution

1280×720 (720p)

Video Duration

2–5 seconds per generation

Generation Speed

~45 seconds average

Cost

From $0.15 per video

Output Format

MP4

API Compatibility

OpenAI-compatible endpoint

Generation Mode

Asynchronous (webhook or polling)

Supported Inputs

Text prompt, image + text prompt (img2vid)

Key Strengths

Smooth motion, cinematic quality, Asian aesthetics

Languages

Multilingual prompts (English, Chinese, others)

Sample outputs

Generated with wan-video-2.1 on Fluxpool.

Try wan-video-2.1

Free to try  •  50 generations included  •  No credit card

API access

Generate video with 8 lines of code. OpenAI-compatible.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.fluxpool.ai/v1",
    api_key="fp_your_api_key"
)

response = client.chat.completions.create(
    model="wan-video-2.1",
    messages=[{
        "role": "user",
        "content": "A lantern festival over a mountain lake, cinematic aerial"
    }],
    extra_body={"type": "video", "duration": 5, "resolution": "1280x720"}
)

# Video generation is async — poll for result or use webhooks
video_url = response.choices[0].message.content
print(video_url)

Video generation is asynchronous. Use webhooks for production workflows. Read webhooks docs →

What to build with wan-video-2.1

Related models

Compare video generation models or pair with an image model.

Start generating video.

50 free generations  •  No credit card required