Wan 2.1 Plus API

alibaba/wan2.1-t2v-plus
Wan2.1 Plus by Alibaba is an advanced text-to-video AI model optimized for generating high-quality 720P videos from text prompts.
Output
$0.5 / gen
Released
Nov 20, 2025

Overview

Alibaba's Wan2.1 Plus is an advanced AI model specialized in text-to-video generation, delivering high-quality, cinematic video outputs with enhanced precision and efficiency. It integrates sophisticated multi-modal understanding to translate textual prompts into visually coherent videos, supporting large-scale video synthesis with detailed control over motion and scene composition.

‍

Technical Specification

Performance Benchmarks

  • Video Generation Quality: High fidelity in dynamic motions, facial expressions, and object interactions
  • Multi-step Reasoning: Strong contextual understanding of complex prompts for video synthesis
  • Instruction Following: Enhanced adherence to user prompts and physical realism in generated videos

Key Capabilities

  • Text-to-Video Synthesis: Generates smooth, contextually accurate videos from natural language descriptions
  • Multi-modal Scene Understanding: Integrates scene layout, colors, lighting, and movement for cinematic effects
  • Fine Control: Supports detailed prompt-based tuning for aesthetic parameters such as lighting, angle, and color tone

API Pricing

  • $0.65 per video

‍

Code Sample

‍

Comparison with Other Models

  • Vs. Wan2.2-T2V: Wan2.1-T2V-Plus offers solid performance with a focus on 1080P video pricing, while Wan2.2 advances further with larger parameter models and multi-expert architecture for enhanced aesthetics and efficiency
  • Vs. Gemini 2.5 Flash: Wan2.1 provides competitive text-to-video capabilities, especially valuable for cost-sensitive 1080P generation tasks
  • Vs. OpenAI GPT-4 Vision: Wan2.1 emphasizes dedicated video synthesis from text with higher resolution pricing support, compared to GPT-4’s broader multimodal conversation

Limitations

  • Some generated videos may include minor artifacts or inconsistencies due to prompt complexity; advanced tuning can mitigate but not fully eliminate these effects
  • Currently optimized primarily for 5-second video clips, longer video generation may require additional processing

Use cases

  • Creative Content Production: Filmmaking, advertising, and storyboarding requiring high-definition video output from text
  • Visual Storytelling: Bringing textual narratives to life with dynamic and richly detailed visuals
  • Interactive Media and Entertainment: Development of visual assets from script or dialogue inputs
  • Business Presentations and Marketing: Generating tailored video content to enhance communication impact

‍

How to use Wan 2.1 Plus API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to alibaba/wan2.1-t2v-plus.
import requests, time

headers = {"Authorization": "Bearer " + AIMLAPI_KEY}
job = requests.post(
    "https://api.aimlapi.com/v2/video/generations",
    headers=headers,
    json={
      "model": "alibaba/wan2.1-t2v-plus",
      "prompt": "A serene timelapse of clouds over a mountain range"
    },
).json()
gid = job["id"]

while True:
    res = requests.get(f"https://api.aimlapi.com/v2/video/generations?generation_id={gid}", headers=headers).json()
    if res.get("status") in ("completed", "error"):
        break
    time.sleep(5)
print(res["video"]["url"])
const headers = {
  Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
  "Content-Type": "application/json",
};
const job = await (await fetch("https://api.aimlapi.com/v2/video/generations", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model": "alibaba/wan2.1-t2v-plus",
    "prompt": "A serene timelapse of clouds over a mountain range"
  }),
})).json();

let res;
do {
  await new Promise((r) => setTimeout(r, 5000));
  res = await (await fetch(`https://api.aimlapi.com/v2/video/generations?generation_id=${job.id}`, { headers })).json();
} while (!["completed", "error"].includes(res.status));
console.log(res.video.url);
# submit the generation — the response contains the job "id"
curl -X POST https://api.aimlapi.com/v2/video/generations \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"alibaba/wan2.1-t2v-plus","prompt":"A serene timelapse of clouds over a mountain range"}'

# then poll until status is "completed" — video.url holds the result
curl "https://api.aimlapi.com/v2/video/generations?generation_id={id}" -H "Authorization: Bearer $AIMLAPI_KEY"

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Wan 2.1 Plus API Pricing

TypePrice
Output
$0.5 / gen

Wan 2.1 Plus vs other models

ModelInputOutputContextBest for
Wan 2.1 Plus
This page
$0.5 / gen
Video generation
$0.2 / sec (variable)
Video generation
$1.95 / 1M tokens
$0.10136 / sec
Video generation
$0.0711 / sec
Cinematic video + native audio

Frequently asked questions

Wan 2.1 Plus takes image, text, video as input and returns video.

Wan 2.1 Plus became available on November 20, 2025.

Wan 2.1 Plus is priced at $0.65 / gen.

Wan 2.1 Plus is billed per generation — a fixed charge per output rather than by prompt length.

Yes, Wan 2.1 Plus accepts image input as well as a text prompt.

Wan 2.1 Plus was built by Alibaba Cloud.

Send a request to v2/generate/video/alibaba/generation with alibaba/wan2.1-t2v-plus as the model id.

Yes. Wan 2.1 Plus is served through AI/ML API, so the same key and endpoint format used for other models applies.

Start building with Wan 2.1 Plus

Get API Key
1000+ models, one API.