Video

Wan 2.7 R2V API

Wan 2.7 R2V API (wan2.7-r2v) on APIMart runs Alibaba's Wan 2.7 reference-to-video model. Give it up to 5 reference images and videos of characters, props or scenes, cite them in the prompt, and it generates a new 2 to 15 second shot at 720P or 1080P that keeps their look, with an optional reference voice for each character.

Reference to VideoUp to 5 References2–15 SecondsReference Voice

Get API Key API Docs

Service Highlights

Official Discounts
Pay-as-you-go
Fast & Low Latency

Input

Model

Prompt *

28/5000

Negative Prompt

Duration5s

Resolution

Seed

Aspect Ratio

Prompt Extend

Watermark

First Frame

Reference Image

Content Moderation

Audio

Click to upload reference audio

WAV, MP3 (max 15MB)

Reference Video

Output

Video link valid for 72 hours

Wan 2.7 R2V API Pricing

Transparent pricing with no hidden fees. Pay only for what you use.

Variant	Tier	GoldCurrent price	Platinum	Diamond	Official	Your savings
`wan2.7-r2v`	720P	0.664Credits(~$0.0664)/sec	0.6308Credits(~$0.0631)/sec	0.5976Credits(~$0.0598)/sec	0.83Credits(~$0.083)/sec	20%
`wan2.7-r2v`	1080P	1.096Credits(~$0.1096)/sec	1.0412Credits(~$0.1041)/sec	0.9864Credits(~$0.0986)/sec	1.37Credits(~$0.137)/sec	20%

* Actual costs are subject to final output.

Wan 2.7 R2V API - Alibaba Wan Reference to Video

Use the Wan 2.7 R2V API on APIMart to turn reference images or videos of characters, props and scenes into a new 2 to 15 second video at 720P or 1080P, with an optional voice sample per character and per-second billing.

Get API Key

50K+

Active Users

99.9%

Uptime

Faster

—

Cost Savings

Key Features of the Wan 2.7 R2V API

How wan2.7-r2v uses reference images, videos and voices

Reference to Video with the Wan 2.7 R2V API

Send images or clips of a character, prop or location and describe a new scene. Wan 2.7 R2V keeps the referenced subjects recognizable in the new shot.

Up to 5 Reference Images and Videos

Combine reference images (image_with_roles) and reference videos (video_urls), up to 5 in total, and cite them in the prompt as image 1, image 2 or video 1.

A Reference Voice for Each Character

Attach a voice sample URL to a reference image with reference_voice to control how that character sounds in the generated video.

Optional First Frame

Give one image the first_frame role to fix the opening shot. The aspect ratio then follows that image and size is ignored.

2–15 Second Clips

Set duration to any whole number from 2 to 15 seconds. When the references include a video, the range is 2 to 10 seconds.

720P and 1080P Output

1080P is the default and 720P costs less per second. size accepts 16:9, 9:16, 1:1, 4:3 or 3:4.

Negative Prompts, Seeds and Prompt Rewriting

Exclude unwanted content with a negative prompt of up to 500 characters, reuse a seed for similar results and keep prompt rewriting on for short prompts.

A Dedicated Model for Reference Work

wan2.7-r2v is separate from wan2.7, which generates from text, frames or a clip to continue, and from wan2.7-videoedit, which edits an existing video.

What You Can Build with the Wan 2.7 R2V API

Workflows built on reference images, reference videos and character voices

Mascot and Character Series

Keep a brand mascot or recurring character looking the same across every short video.

Products Placed in New Scenes

Reference a product photo and a location, then generate a clip of the product in use there.

Multi-Character Scenes

Bring two referenced characters together in one shot, such as the person in image 1 meeting the person in image 2.

Characters with Their Own Voice

Pair each character image with a voice sample so dialogue sounds consistent from clip to clip.

New Shots from Existing Footage

Use a short reference clip to carry a character or setting from earlier footage into a new scene.

Storyboards with Consistent Casts

Generate several shots of the same cast for a pitch or animatic before full production.

How to Get a Wan 2.7 R2V API Key and Start Building

From sign-up to your first Wan 2.7 R2V video in three steps

Create Your Wan 2.7 R2V API Key

→

Test Wan 2.7 R2V in the Playground

Upload reference images or videos above, write a prompt that cites them, and check the cost estimate before you write code.

→

Integrate the Wan 2.7 R2V API

Submit tasks from your backend with the example below, then poll for the result.

Start Creating

Wan 2.7 R2V API Example: Reference Image and Reference Video

Call the Wan 2.7 R2V API on APIMart with one POST request. Generation is asynchronous: submit a task, then poll the task endpoint for the video URL.

1
Authenticate Wan 2.7 R2V requests
Save your APIMart key in the APIMART_API_KEY environment variable and send it as Authorization: Bearer <key> on every request.
2
Submit a Wan 2.7 R2V task
POST /v1/videos/generations with model wan2.7-r2v, a prompt that cites your references, and image_with_roles or video_urls. The task ID is in data[0].task_id.
3
Get the Wan 2.7 R2V video
Poll GET /v1/tasks/{task_id} until status is completed, then read the video URL from data.result.videos[0].url[0] and save the file to your own storage.
See the Wan 2.7 R2V API reference for every parameter, reference rule and response field.

POST /v1/videos/generations

curl -X POST https://api.apimart.ai/v1/videos/generations \
  -H "Authorization: Bearer $APIMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-r2v",
    "prompt": "The character in image 1 walks through a sunlit flower market, waves at the camera and smiles, gentle handheld shot",
    "image_with_roles": [
      {
        "url": "https://example.com/character.jpg",
        "role": "reference_image"
      }
    ],
    "duration": 5,
    "resolution": "720P",
    "size": "16:9"
  }'

import os
import time
import requests

API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}

# 1. Submit the generation task
payload = {
  "model": "wan2.7-r2v",
  "prompt": "The character in image 1 walks through a sunlit flower market, waves at the camera and smiles, gentle handheld shot",
  "image_with_roles": [
    {
      "url": "https://example.com/character.jpg",
      "role": "reference_image"
    }
  ],
  "duration": 5,
  "resolution": "720P",
  "size": "16:9"
}
resp = requests.post(f"{API_BASE}/v1/videos/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]

# 2. Poll the task until it finishes
for _ in range(200):
    task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
    task_resp.raise_for_status()
    task = task_resp.json()["data"]
    if task["status"] == "completed":
        print(task["result"]["videos"][0]["url"][0])
        break
    if task["status"] == "failed":
        raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
    time.sleep(10)
else:
    raise TimeoutError(f"task {task_id} did not finish in time")

curl -X POST https://api.apimart.ai/v1/videos/generations \
  -H "Authorization: Bearer $APIMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-r2v",
    "prompt": "The character in video 1 sits at a café window reading a book while rain streaks the glass",
    "video_urls": [
      "https://example.com/character.mp4"
    ],
    "duration": 5,
    "resolution": "720P",
    "size": "16:9"
  }'

TASK_ID="task_xxx"  # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
  -H "Authorization: Bearer $APIMART_API_KEY"

Wan 2.7 R2V API Parameters

Parameter	Type	Required	Default	Description
`model`	string	Required	Default: wan2.7-r2v	Use wan2.7-r2v.
`prompt`	string	Required	Default: —	Scene description up to 5,000 characters. Cite references as image 1, image 2, video 1 in input order.
`image_with_roles`	array	Optional	Default: —	Images with url and role (reference_image or first_frame), plus an optional reference_voice URL. Required if video_urls is empty.
`video_urls`	array	Optional	Default: —	Reference clips (mp4 or mov, 1–30 seconds, up to 100 MB). Images plus videos up to 5. Required if image_with_roles is empty.
`negative_prompt`	string	Optional	Default: —	Content to avoid, up to 500 characters.
`resolution`	string	Optional	Default: 1080P	720P or 1080P.
`duration`	integer	Optional	Default: 5	2 to 15 seconds, or 2 to 10 when a reference video is included.
`size`	string	Optional	Default: 16:9	16:9, 9:16, 1:1, 4:3 or 3:4. Ignored when a first_frame image is set.
`prompt_extend`	boolean	Optional	Default: true	Rewrite and enrich the prompt. Helps short prompts but adds time.
`seed`	integer	Optional	Default: —	0 or higher. The same seed gives similar, not identical, results.
`watermark`	boolean	Optional	Default: false	Add an AI Generated watermark.
`nsfw_check`	boolean	Optional	Default: false	Moderate the prompt and input images with omni-moderation-latest before submission.

User Reviews for WAN 2.7

Real feedback from creators and developers using WAN 2.7 worldwide. These reviews describe experiences with the Wan 2.7 series.

“The consistency of WAN 2.7 is amazing! Character images remain stable across multiple clips, which was previously hard to achieve.”

Wei Zhang

Independent Animator

“As a developer, I value stability and speed. WAN 2.7 on APIMart delivers great performance with an easy-to-use API.”

David Chen

Full-Stack Engineer

“The image-to-video feature saved me so much post-production time. I just provide the keyframes and let WAN 2.7 do the rest.”

Ming Li

Illustrator

“WAN 2.7 dramatically cut our short-form video turnaround. Cinematic camera moves and stable character consistency make our brand stand out on social.”

Sarah Kim

Content Creator

Compare Alibaba Wan Video Models

Compare every Alibaba Wan video model on APIMart. One API key calls all of them, billed per second of video.

Model	Best for	Resolution	Duration
Wan 3.0 API	Longest Wan clips, with first and last frames or image, video, audio, document and webpage references	480P / 720P / 1080P	2–30 s
Wan 3.0 Prime API	Same parameters as Wan 3.0 under a separate model and price	480P / 720P / 1080P	2–30 s
Wan 2.7 API	Text to video, first and last frames, video continuation and audio-driven clips	720P / 1080P	2–15 s
Wan 2.7 R2V APIThis page	Keeping characters consistent from reference images or videos	720P / 1080P	2–15 s
Wan 2.7 Video Edit API	Editing or restyling an existing video with an instruction	720P / 1080P	Follows source, up to 10 s
Wan 2.6 API	Multi-shot text to video and image to video with audio and effect templates	720p / 1080p	5 / 10 / 15 s
Wan 2.6 I2V API	Dedicated image to video from a single first frame	720p / 1080p	5 / 10 / 15 s
Wan 2.6 I2V Flash API	Image to video at any length from 2 to 15 seconds, with or without audio	720p / 1080p	2–15 s
Wan 2.5 API	Short clips that always include sound, with a low-cost 480p tier	480p / 720p / 1080p	5 / 10 s

Wan 2.7 R2V API FAQ

Answers about wan2.7-r2v references, voices, parameters and pricing

What is Wan 2.7 R2V (wan2.7-r2v)?

Wan 2.7 R2V is Alibaba's Wan 2.7 reference-to-video model. It generates a new 2 to 15 second video at 720P or 1080P from reference images and videos of characters, props or scenes. On APIMart its model ID is wan2.7-r2v.

How does Wan 2.7 R2V reference-to-video work?

Send reference images in image_with_roles and/or reference clips in video_urls, then write a prompt that cites them in input order, for example: the character in image 1 enters the scene in image 2. The model keeps the referenced subjects consistent in the new shot.

How many references can I use?

Up to 5 in total across images and videos. Reference videos must be mp4 or mov, 1 to 30 seconds, 240 to 4096 pixels per side, aspect ratio between 1:8 and 8:1, and up to 100 MB.

Can I control a character's voice?

Yes. Add reference_voice, a URL to a voice sample, to a reference image in image_with_roles. The character from that image uses that voice in the generated video.

Can I set the first frame in Wan 2.7 R2V?

Yes. Give one image the role first_frame in image_with_roles. The video starts from that image, and its aspect ratio replaces the size parameter.

How long and what resolution are Wan 2.7 R2V videos?

duration is any whole number from 2 to 15 seconds (default 5), or 2 to 10 seconds when a reference video is included. resolution is 720P or 1080P (default 1080P), and size is 16:9, 9:16, 1:1, 4:3 or 3:4 (default 16:9).

Wan 2.7 R2V, Wan 2.7 or Wan 2.7 Video Edit: which should I use?

Use Wan 2.7 R2V when characters or objects must match your reference images or videos. Use Wan 2.7 (wan2.7) to generate from text, first and last frames or a clip to continue, and Wan 2.7 Video Edit (wan2.7-videoedit) to change an existing video with an instruction.

What parameters does the Wan 2.7 R2V API support?

model (wan2.7-r2v) and prompt are required, plus at least one of image_with_roles or video_urls. Optional fields: negative_prompt, resolution, duration, size, prompt_extend (default true), seed, watermark and nsfw_check.

How do I call the Wan 2.7 R2V API and get the video?

POST to /v1/videos/generations and read the task ID from data[0].task_id. Poll GET /v1/tasks/{task_id} every few seconds until status is completed, then read data.result.videos[0].url[0].

How much does the Wan 2.7 R2V API cost per second?

Wan 2.7 R2V is billed per second of video, and 1080P costs more per second than 720P. See the pricing table on this page; Gold members save 20%, and Platinum and Diamond members save up to 28%.

Is Wan 2.7 R2V free or open source?

No. APIMart has no free quota for Wan 2.7 R2V; you pay per second for each task. Alibaba offers Wan 2.7 R2V as a hosted API and has not released its weights.

How do I get a Wan 2.7 R2V API key?

Sign up for APIMart, add balance and create a key on the API Keys page. Send it as Authorization: Bearer <key>. The same key works for every Wan model and the rest of the APIMart catalog.

Related Models

Explore more models in the same category.

View All Models →

Wan 2.7 R2V API

Wan 2.7 R2V API Pricing

Wan 2.7 R2V API - Alibaba Wan Reference to Video

Key Features of the Wan 2.7 R2V API

What You Can Build with the Wan 2.7 R2V API

How to Get a Wan 2.7 R2V API Key and Start Building

Create Your Wan 2.7 R2V API Key

Test Wan 2.7 R2V in the Playground

Integrate the Wan 2.7 R2V API

Wan 2.7 R2V API Example: Reference Image and Reference Video

Authenticate Wan 2.7 R2V requests

Submit a Wan 2.7 R2V task

Get the Wan 2.7 R2V video

Wan 2.7 R2V API Parameters

User Reviews for WAN 2.7

Compare Alibaba Wan Video Models

Wan 2.7 R2V API FAQ

What is Wan 2.7 R2V (wan2.7-r2v)?

How does Wan 2.7 R2V reference-to-video work?

How many references can I use?

Can I control a character's voice?

Can I set the first frame in Wan 2.7 R2V?

How long and what resolution are Wan 2.7 R2V videos?

Wan 2.7 R2V, Wan 2.7 or Wan 2.7 Video Edit: which should I use?

What parameters does the Wan 2.7 R2V API support?

How do I call the Wan 2.7 R2V API and get the video?

How much does the Wan 2.7 R2V API cost per second?

Is Wan 2.7 R2V free or open source?

How do I get a Wan 2.7 R2V API key?

Related Models

Latest Wan 2.7 R2V articles

Key Features of the Wan 2.7 R2V API

What You Can Build with the Wan 2.7 R2V API

How to Get a Wan 2.7 R2V API Key and Start Building

Create Your Wan 2.7 R2V API Key

Test Wan 2.7 R2V in the Playground

Integrate the Wan 2.7 R2V API

User Reviews for WAN 2.7

Wan 2.7 R2V API FAQ

What is Wan 2.7 R2V (wan2.7-r2v)?

How does Wan 2.7 R2V reference-to-video work?

How many references can I use?

Can I control a character's voice?

Can I set the first frame in Wan 2.7 R2V?

How long and what resolution are Wan 2.7 R2V videos?

Wan 2.7 R2V, Wan 2.7 or Wan 2.7 Video Edit: which should I use?

What parameters does the Wan 2.7 R2V API support?

How do I call the Wan 2.7 R2V API and get the video?

How much does the Wan 2.7 R2V API cost per second?

Is Wan 2.7 R2V free or open source?

How do I get a Wan 2.7 R2V API key?

Related Models