Wan 2.7 Reference to Video API

alibaba/wan2.7-r2v
Wan 2.
Output
$0.1 / sec (variable)
Released
Apr 28, 2026

Overview

What is Wan 2.7 Reference to Video API?

Wan 2.7 R2V — a reference-to-video model by Alibaba Cloud that generates videos using reference images or videos. It enables character, motion, and style transfer.

Technical Specifications
- Supported inputs: Image
- Output: Video

Performance Benchmarks
[embed]

Wan 2.7 Reference to Video API Pricing
- Pricing on request

Where to Use Wan 2.7 Reference to Video

Short-form video generation
Create clips for social, ads, and product demos from text or image prompts.

Previsualization and storyboards
Rapidly prototype motion concepts before committing to production.

Use cases

Character-driven storytelling is a documented use case, where a reference subject can be kept visually consistent while being placed into new video scenes.

Multi-character interaction scenes are a documented use case, with the model supporting videos that feature one or more characters while preserving their appearance across scenes.

Content production and social video are documented use cases, including branded video content and campaigns that need a specific person or spokesperson to remain consistent.

Video dubbing and localization are also documented use cases, with the model used to generate dubbed or localized video while preserving the speaker’s characteristics.

How to use Wan 2.7 Reference to Video API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to alibaba/wan2.7-r2v.

import requests, time

headers = {"Authorization": "Bearer " + AIMLAPI_KEY}
job = requests.post(
   "https://api.aimlapi.com/v2/video/generations",
   headers=headers,
   json={
     "model": "alibaba/wan2.7-r2v",
     "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/wan2.7-r2v",
    "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/wan2.7-r2v","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 2.7 Reference to Video API Pricing

TypePrice
Output
$0.1 / sec (variable)

Wan 2.7 Reference to Video vs other models

ModelInputOutputContextBest for
$0.1 / sec (variable)
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 2.7 Reference to Video takes image as input and returns video.

Wan 2.7 Reference to Video became available on April 28, 2026.

Wan 2.7 Reference to Video is priced at $0.13 / sec (variable).

Wan 2.7 Reference to Video is billed per generation — a fixed charge per output rather than by prompt length.

Yes, Wan 2.7 Reference to Video accepts image input as well as a text prompt.

Wan 2.7 Reference to Video was built by Alibaba Cloud.

Use alibaba/wan2.7-r2v as the model id on AI/ML API.

Yes. Wan 2.7 Reference to Video is served through AI/ML API, so the same key and endpoint format used for other models applies.

It generates videos from reference images or videos, enabling character, motion, and style transfer.

Yes, its reference-to-video feature is designed for character transfer, helping maintain consistency.

Start building with Wan 2.7 Reference to Video

Get API Key
1000+ models, one API.