Skip to main content
Available now on ModelsLab · Video Generation

Wan 2.1 API — Upgraded to Wan 2.2Wan 2.1 is now Wan 2.2 on ModelsLab. Same architecture, cheaper per clip.

Try Wan 2.2 FreeAPI Documentation

Wan 2.1 — Alibaba Cloud's video workhorse

Wan 2.1

Alibaba Cloud's video model

Wan 2.1 is Alibaba Cloud's video generation model. Text-to-video and image-to-video from the same API surface, with strong motion realism and subject consistency.

Open-source heritage

Proven community quality

Wan 2.1 is the open-source-friendly release that made Wan popular for bulk video workloads. Lower per-clip cost than Wan 2.2 or 2.7 while still delivering production-ready output.

Text-to-Video

Cinematic generation

Generate short clips from text prompts. Wan 2.1 handles camera movement, subject consistency, and natural physics at 720p-1080p.

Image-to-Video

Animate stills

Turn a single image into motion. Optional motion prompt for direction, speed, and intensity of the animation.

Pricing

Cheapest Wan variant

Wan 2.1 is priced lower than Wan 2.2 / 2.7 — typically ~$0.10 per 5-second clip on ModelsLab. Ideal for high-volume workflows where cost matters.

One API Key

No Alibaba Cloud account

Call Wan via the ModelsLab REST API. Same key works for every other video model (Kling, Seedance, Runway Aleph, Veo).

Webhooks

Async callbacks

Pass a webhook URL — ModelsLab POSTs the MP4 to your endpoint when generation completes.

SDKs

Python & JavaScript

Official SDKs wrap every Wan endpoint. REST + OpenAPI for autogenerated clients.

Examples

See what Wan 2.1 can do

Copy any prompt below and try it yourself in the playground.

Cinematic landscape

“a cinematic shot of a red fox walking through snow, depth of field, golden hour light”

Product reveal

“a sleek smartphone rotating on a minimalist pedestal, studio lighting”

Character animation

“a dancer performing fluid contemporary moves in a sunlit studio”

Nature scene

“a waterfall crashing into a pool at dusk, natural ambient motion”

For Developers

A few lines of code.
Cheapest Wan variant. Same API.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per clip, no minimums
  • Python and JavaScript SDKs, plus REST API
API Documentation 
import requests


response = requests.post(
    "https://modelslab.com/api/v7/video-fusion/text-to-video",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "a cinematic shot of the subject with natural motion",
  "model_id": "wan-2.2-i2v",
  "init_image": "https://example.com/source.jpg",
  "num_frames": 120,
  "output_type": "mp4"
}
)
print(response.json())

FAQ

Common questions about Wan 2.1 API — Upgraded to Wan 2.2

Read the docs

Wan 2.1 was the original open-source Wan release from Alibaba Cloud. The current production endpoint on ModelsLab is Wan 2.2 (/models/modelslab/wan-2.2-i2v), which is a direct drop-in successor — same architecture, backward-compatible prompts, improved motion coherence. Wan 2.7 is also available for multimodal workflows. Use Wan 2.2 unless you have a specific reason to target v2.1 parameters.

Wan 2.2 is Alibaba Cloud's incremental upgrade over Wan 2.1 — same motion model lineage, backward-compatible prompt structure, better temporal coherence on longer clips. Most prompts that worked on 2.1 produce equal-or-better output on 2.2 without code changes.

Wan 2.2 on ModelsLab is priced around $0.10 per 5-second 720p clip — typically the cheapest cinematic video model available. Transparent per-call pricing with free credits on signup.

Wan 2.2 is the cheapest and strongest for bulk video generation workloads. Wan 2.7 adds multimodal inputs (text-to-image + image-edit + text-to-video + image-to-video in one family) at a slightly higher per-clip price. Both run behind one ModelsLab API key.

Yes. Call /models/modelslab/wan-2.2-i2v with an input image plus optional motion prompt. Returns a short animated MP4 clip.

Each Wan call produces 5-10 seconds. For longer sequences, generate multiple clips and stitch them at scene boundaries — a common pattern for 30-60s social video.

Yes. Every new ModelsLab account gets free credits — no credit card required. Use them to test Wan 2.2 against Kling, Seedance, Runway Aleph and Veo before picking a paid plan.

Yes. Pass a webhook URL and ModelsLab POSTs the completed MP4 URL to your endpoint when generation finishes.

Ready to create?

Start generating with Wan 2.1 API — Upgraded to Wan 2.2 on ModelsLab.

Try Wan 2.2 FreeAPI Documentation