What is the official Wan 3.0 API model ID?

Alibaba Cloud's official API uses the model ID `wan3.0-video`. CometAPI currently lists its corresponding catalog model as `wan3.0`.

What makes Wan 3.0 different from Wan 2.7?

Wan 3.0 extends single-generation video to 30 seconds and adds broader Omni-Reference capabilities, including documents and web pages as creative inputs.

What resolutions does the Wan 3.0 API support?

Wan 3.0 supports 480P, 720P and 1080P output. The official API documentation does not list 4K output.

Does Wan 3.0 generate audio together with video?

Yes. Wan 3.0 supports native audiovisual generation, and the official API provides an audio parameter that is enabled by default.

Can Wan 3.0 turn a PDF or PowerPoint into a video?

Yes. Wan 3.0 supports document-based generation and accepts formats including DOC, XLS, PPT, PDF, TXT, KEY, PAGES, NUMBERS and MD, with a limit of one file or link up to 100 MB and 50 pages.

Can Wan 3.0 generate a 30-second video in one API call?

Yes. Wan 3.0 supports native video generation of up to 30 seconds in a single generation, with smart-duration and video-extension capabilities.

Can Wan 3.0 use multiple reference images, videos and audio files?

Yes. Wan 3.0 supports reference-based generation using images, videos, audio and other supported media, allowing characters, objects, environments and actions to be controlled through references.

Aliyun

Available Popular

wan3.0

Wan3.0 API

From fast verification to cinematic output, billing is based on the generated video duration, selecting the appropriate resolution, and turning every generation into a planned creative investment activity rule

Starting price

$0.05 / second

Usage-based billing

API health

Available

Production endpoint

Response

Async ready

Observed API response

Released

Aug 24, 2026

Aliyun

Playground

Try Wan3.0 with a real request, review its parameters and validate the output before integrating the API.

Overview

A practical overview of Wan3.0, including important behavior and integration considerations.

Technical Specifications of Wan 3.0

Specification	Wan 3.0
Model Type	Multimodal all-in-one video generation model
Model Status	Public API preview
Input Types	Text, image, video, audio, documents, web pages
Video Generation	Text-to-video, image-to-video, reference-to-video
Video Editing	Instruction-based and reference-based editing
Maximum Duration	30 seconds in a single generation
Output Resolution	480P, 720P, 1080P
Native Audio-Visual Generation	Yes
Reference Assets	Up to 20 multimodal reference assets
Document Inputs	DOC, XLS, PPT, PDF, TXT, KEY, PAGES, NUMBERS, MD
Maximum Document Size	100 MB
Maximum Document Pages	50 pages
API Access	Alibaba Cloud Model Studio API preview
API Generation Mode	Asynchronous
480P Price	$0.05/sec
720P Price	$0.10/sec
1080P Price	$0.20/sec

Wan 3.0 is Alibaba Cloud's latest all-in-one multimodal video generation model, officially launched in August 2026. Its most significant upgrade over previous Wan generations is not simply higher visual quality, but the consolidation of text, images, video, audio, documents, and web pages into a single creative workflow. Alibaba Cloud describes the model as supporting native 30-second video generation, multimodal reference inputs, synchronized audio-visual generation, and precision video editing.

What Is Wan 3.0?

Wan 3.0 is Alibaba's next-generation multimodal video generation model designed to turn text, images, video, audio, documents, and web content into coherent video.

Earlier AI video workflows often required several specialized models: one for text-to-video, another for image-to-video, another for reference consistency, and separate tools for editing or audio. Wan 3.0 moves toward an all-in-one production model where these inputs can be combined around a single creative instruction.

Its headline capability is native 30-second generation. Instead of producing a short 5- or 10-second clip that must be repeatedly extended and stitched together, Wan 3.0 can generate a continuous 30-second sequence in one pass. Alibaba's demonstrations show the model maintaining characters, environments, actions, camera movement, dialogue, and sound across longer scenes.

Another major change is Omni-Reference. Developers can use multiple reference assets to establish characters, products, environments, motion, or other visual characteristics. The official Wan 3.0 repository describes support for up to 20 reference assets, while Alibaba Cloud's product page emphasizes the ability to combine images, text, video, audio, documents, and web pages as creative references.

This makes Wan 3.0 less like a simple prompt-to-video generator and more like a multimodal creative production engine.

Main Features of Wan 3.0

Native 30-second video generation: Wan 3.0 can generate up to 30 seconds of video in a single pass, with intelligent duration selection and video extension capabilities.
Omni-Reference: Text, images, video and audio can be combined as references. Wan 3.0 also extends reference-based generation to documents and web pages.
Document-to-video: PPT, PDF, DOC, XLS, TXT, KEY, PAGES, NUMBERS and MD files can be used as creative inputs, allowing presentations, reports and structured information to become video content.
Native audiovisual generation: Wan 3.0 can generate video and sound together, supporting dialogue, environmental audio and music-oriented audio visual scenes.
Reference consistency: The model is designed to preserve characters, props, environments, spatial relationships and styles across reference-driven generations.
Video editing: Wan 3.0 supports modifications to generated visual content, plot and dialogue rather than requiring every iteration to start from scratch.

How Does Wan 3.0 Compare With Other Video Models?

Model	Native Duration	Image-to-Video	Reference Control	Audio	Document/Web Input	Main Strength
Wan 3.0	30s	✓	Strong	✓	✓	All-in-one multimodal production
Wan 2.7	15s	✓	✓	✓	Limited	Established Wan video workflows
Grok Imagine Video 1.5	Up to 15s	✓	✓	✓	—	Fast short-form creative video
Veo	Model-dependent	✓	✓	✓	Multimodal	Cinematic generation
Kling	Model-dependent	✓	✓	✓	—	Character and motion generation
Seedance	Model-dependent	✓	✓	✓	—	Creative and multi-shot video

The key differentiator is input breadth.

Compared with Grok Imagine Video 1.5, Wan 3.0 goes substantially further toward an all-in-one production workflow. Grok is focused on short video generation with text, image, and reference workflows, while Wan 3.0 additionally incorporates documents, web pages, audio, and video as direct creative references.

Compared with Wan 2.7, the biggest architectural/product-level change is the move toward a unified multimodal workflow and a 30-second native generation ceiling, compared with the previous generation's shorter clips. Alibaba Cloud's current Wan 3.0 materials explicitly position the model around long-form narrative and Omni-Reference generation.

Compared with Kling and Veo, Wan 3.0's strongest differentiator is not necessarily that every generated frame will be better. Rather, it is the ability to combine a large amount of source material and maintain that information throughout a longer generation.

For applications where the input is simply "write this prompt and generate a cinematic clip," other models may remain competitive. For workflows where the input is "here is a product image, character reference, PDF, spreadsheet, audio sample, and creative brief—turn them into a coherent video," Wan 3.0 becomes much more compelling.

Representative Use Cases for Wan 3.0

1. AI filmmaking and story production

The 30-second single-generation capability makes Wan 3.0 useful for scenes requiring continuous camera movement, dialogue and multiple actions without stitching numerous short clips.

2. Product advertising

A product image or collection of references can be combined with a director-style prompt to create product demonstrations, UGC advertisements and cinematic brand videos.

3. Presentation-to-video generation

Wan 3.0 can process PPT, PDF, DOC, XLS and other supported document formats, making it suitable for converting reports, presentations and structured information into visual narratives.

4. Character-consistent video

Reference images, video and other media can be used to establish characters, objects and environments before generating a scene.

The 30-second duration and vertical 9:16 aspect ratio make Wan 3.0 suitable for short-form social content, advertisements and narrative clips.

6. Video editing and iteration

Wan 3.0 can modify existing generated content, including visual elements, story content and dialogue, enabling iterative creative workflows.

Wan 3.0 API Parameters

The official API uses an asynchronous video-generation endpoint. A simplified request contains a model, input, and parameters object.

Important parameters include:

Parameter	Description
model	wan3.0-video
input.prompt	Director-style generation instruction
input.media	Reference images, videos, audio, files or web resources
parameters.resolution	480P, 720P, 1080P
parameters.ratio	adaptive, 16:9, 4:3, 1:1, 3:4, 9:16
parameters.duration	2–30 seconds; -1 enables smart duration
parameters.audio	Whether to include an audio track
parameters.seed	Random seed for reproducibility
parameters.watermark	Whether to add a watermark

The official documentation states that when no video input is supplied, duration can be an integer from 2 to 30 seconds. When video input is supplied, the input and output duration together must remain within the supported total duration.

How to Use Wan 3.0 API on CometAPI

For developers using multiple AI video models, CometAPI can serve as a unified access layer for experimenting with Wan 3.0 alongside other video-generation models.

A typical workflow is:

Create or log in to a CometAPI account.
Obtain a CometAPI API key.
Select the Wan 3.0 model endpoint.
Submit a text-to-video, image-to-video, or reference-based generation request.
Specify resolution, duration, aspect ratio, and other supported parameters.
Monitor the asynchronous generation task.
Retrieve the generated video when processing completes.

The exact CometAPI endpoint and supported parameters should be checked against the current CometAPI Wan 3.0 integration before implementation, particularly because the upstream Alibaba API is still in preview.

FAQ

Pricing

Use the quick estimate above for a single run, then review the full CometAPI and official-price comparison.

5-second test

$0.25

Estimated CometAPI usage cost

10-second test

$0.5

Estimated CometAPI usage cost

15-second test

$0.75

Estimated CometAPI usage cost

Pricing for Wan3.0

Explore competitive pricing for Wan3.0, designed to fit various budgets and usage needs. Our flexible plans ensure you only pay for what you use, making it easy to scale as your requirements grow. Discover how Wan3.0 can enhance your projects while keeping costs manageable.

Wan 3.0 Video Generation Pricing

From fast verification to cinematic output, billing is based on generated video duration and the selected resolution, turning every generation into a planned creative investment.

Customer-facing model: wan3.0

Output Resolution	Price per Generated Second	5-Second Video
480P	$0.05	$0.25
720P	$0.10	$0.50
1080P	$0.20	$1.00

Supported duration: 2–30 seconds
Billing unit: generated video second
Choose the appropriate output resolution for each generation
Final charge = applicable resolution price × successfully generated video duration

API

Copy a working endpoint and code example, then open the complete API reference when you need every parameter.

One API, production-ready model access

Authenticate once, call the model endpoint and keep the same billing and observability workflow across providers.

POST/v1/videosGET/v1/videos/{task_id}/contentGET/v1/videos/{task_id}

Sample code and API for Wan3.0

Access comprehensive sample code and API resources for Wan3.0 to streamline your integration process. Our detailed documentation provides step-by-step guidance, helping you leverage the full potential of Wan3.0 in your projects.

POST

/v1/videos

GET

/v1/videos/{task_id}/content

GET

/v1/videos/{task_id}

response=$(curl -sS --fail-with-body "https://api.cometapi.com/v1/videos" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F model=wan3.0 \
  -F prompt='A small robot walks through a bright greenhouse with smooth camera movement.' \
  -F seconds=5 \
  -F size=1920x1080) || exit 1

video_id=$(printf '%s' "$response" | sed -n 's/.*"id"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
if [ -z "$video_id" ]; then
  printf 'Missing video ID: %s
' "$response" >&2
  exit 1
fi
printf 'Video ID: %s
' "$video_id"

polls=0
while [ "$polls" -lt 54 ]; do
  status_response=$(curl -sS --fail-with-body "https://api.cometapi.com/v1/videos/${video_id}" \
    -H "Authorization: Bearer $COMETAPI_KEY") || exit 1
  progress=$(printf '%s' "$status_response" | sed -n 's/.*"progress"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
  status=$(printf '%s' "$status_response" | sed -n 's/.*"status"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
  printf 'Progress: %s, Status: %s
' "${progress:-0%}" "${status:-unknown}"
  case "$status" in
    FAILURE|failure|failed|error|cancelled|canceled) exit 1 ;;
    completed|succeeded|success) break ;;
  esac
  [ "$progress" = "100%" ] && break
  polls=$((polls + 1))
  sleep 10
done
if [ "$polls" -ge 54 ]; then
  echo "Video generation did not complete within 9 minutes" >&2
  exit 1
fi

mkdir -p output
output_path="output/${video_id}.mp4"
curl -sS --fail-with-body "https://api.cometapi.com/v1/videos/${video_id}/content" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -o "$output_path"
printf 'Saved: %s (%s bytes)
' "$output_path" "$(wc -c < "$output_path")"

cURL Code Example

response=$(curl -sS --fail-with-body "https://api.cometapi.com/v1/videos" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F model=wan3.0 \
  -F prompt='A small robot walks through a bright greenhouse with smooth camera movement.' \
  -F seconds=5 \
  -F size=1920x1080) || exit 1

video_id=$(printf '%s' "$response" | sed -n 's/.*"id"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
if [ -z "$video_id" ]; then
  printf 'Missing video ID: %s\n' "$response" >&2
  exit 1
fi
printf 'Video ID: %s\n' "$video_id"

polls=0
while [ "$polls" -lt 54 ]; do
  status_response=$(curl -sS --fail-with-body "https://api.cometapi.com/v1/videos/${video_id}" \
    -H "Authorization: Bearer $COMETAPI_KEY") || exit 1
  progress=$(printf '%s' "$status_response" | sed -n 's/.*"progress"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
  status=$(printf '%s' "$status_response" | sed -n 's/.*"status"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
  printf 'Progress: %s, Status: %s\n' "${progress:-0%}" "${status:-unknown}"
  case "$status" in
    FAILURE|failure|failed|error|cancelled|canceled) exit 1 ;;
    completed|succeeded|success) break ;;
  esac
  [ "$progress" = "100%" ] && break
  polls=$((polls + 1))
  sleep 10
done
if [ "$polls" -ge 54 ]; then
  echo "Video generation did not complete within 9 minutes" >&2
  exit 1
fi

mkdir -p output
output_path="output/${video_id}.mp4"
curl -sS --fail-with-body "https://api.cometapi.com/v1/videos/${video_id}/content" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -o "$output_path"
printf 'Saved: %s (%s bytes)\n' "$output_path" "$(wc -c < "$output_path")"

Python Code Example

import os
import time
from pathlib import Path

import requests

# Get your API key from https://www.cometapi.com/console/token, and paste it here
API_KEY = os.environ.get("COMETAPI_KEY") or "<YOUR_COMETAPI_KEY>"
BASE_URL = "https://api.cometapi.com".rstrip("/")

response = requests.post(
    f"{BASE_URL}/v1/videos",
    headers={"Authorization": f"Bearer {API_KEY}"},
    files={
        "model": (None, "wan3.0"),
        "prompt": (None, "A small robot walks through a bright greenhouse with smooth camera movement."),
        "seconds": (None, "5"),
        "size": (None, "1920x1080"),
    },
    timeout=120,
)
response.raise_for_status()
video_id = response.json()["id"]
print(f"Video ID: {video_id}")

deadline = time.monotonic() + 540
while time.monotonic() < deadline:
    response = requests.get(
        f"{BASE_URL}/v1/videos/{video_id}",
        headers={"Authorization": f"Bearer {API_KEY}"},
        timeout=120,
    )
    response.raise_for_status()
    result = response.json()
    data = result.get("data") or result
    progress = data.get("progress", result.get("progress", "0%"))
    status = str(data.get("status", result.get("status", "unknown")))
    print(f"Progress: {progress}, Status: {status}")
    if status.lower() in {"failure", "failed", "error", "cancelled", "canceled"}:
        raise RuntimeError(f"Video generation failed: {result}")
    if progress == "100%" or status.lower() in {"completed", "succeeded", "success"}:
        break
    time.sleep(10)
else:
    raise TimeoutError("Video generation did not complete within 9 minutes")

response = requests.get(
    f"{BASE_URL}/v1/videos/{video_id}/content",
    headers={"Authorization": f"Bearer {API_KEY}"},
    timeout=120,
)
response.raise_for_status()
output_path = Path("output") / f"{video_id}.mp4"
output_path.parent.mkdir(parents=True, exist_ok=True)
output_path.write_bytes(response.content)
print(f"Saved: {output_path} ({output_path.stat().st_size} bytes)")

JavaScript Code Example

import { mkdir, writeFile } from "node:fs/promises";

// Get your API key from https://www.cometapi.com/console/token, and paste it here
const apiKey = process.env["COMETAPI_KEY"] || "<YOUR_COMETAPI_KEY>";
const baseUrl = "https://api.cometapi.com".replace(/\/$/, "");

const form = new FormData();
form.append("model", "wan3.0");
form.append("prompt", "A small robot walks through a bright greenhouse with smooth camera movement.");
form.append("seconds", "5");
form.append("size", "1920x1080");

let response = await fetch(`${baseUrl}/v1/videos`, {
  method: "POST",
  headers: { Authorization: `Bearer ${apiKey}` },
  body: form,
});
if (!response.ok) throw new Error(await response.text());
const { id: videoId } = await response.json();
console.log(`Video ID: ${videoId}`);

const deadline = Date.now() + 540_000;
let completed = false;
while (Date.now() < deadline) {
  response = await fetch(`${baseUrl}/v1/videos/${videoId}`, {
    headers: { Authorization: `Bearer ${apiKey}` },
  });
  if (!response.ok) throw new Error(await response.text());
  const result = await response.json();
  const data = result.data || result;
  const progress = data.progress || result.progress || "0%";
  const status = String(data.status || result.status || "unknown");
  console.log(`Progress: ${progress}, Status: ${status}`);
  if (["failure", "failed", "error", "cancelled", "canceled"].includes(status.toLowerCase())) {
    throw new Error(`Video generation failed: ${JSON.stringify(result)}`);
  }
  if (progress === "100%" || ["completed", "succeeded", "success"].includes(status.toLowerCase())) {
    completed = true;
    break;
  }
  await new Promise((resolve) => setTimeout(resolve, 10_000));
}
if (!completed) throw new Error("Video generation did not complete within 9 minutes");

response = await fetch(`${baseUrl}/v1/videos/${videoId}/content`, {
  headers: { Authorization: `Bearer ${apiKey}` },
});
if (!response.ok) throw new Error(await response.text());
const video = Buffer.from(await response.arrayBuffer());
await mkdir("output", { recursive: true });
const outputPath = `output/${videoId}.mp4`;
await writeFile(outputPath, video);
console.log(`Saved: ${outputPath} (${video.length} bytes)`);

Capabilities

Scan the model facts that matter before you choose an architecture or estimate production workload.

Supported capabilities

Features returned by the existing model API.

text-to-video

image-to-video

Input and output

Inputs

text

Outputs

video

Production profile

Provider: Aliyun
Context: Model specific
Commercial use: Supported

Use cases

Use Wan3.0 for production workflows that match its video capabilities, then compare alternatives before committing to a long-term integration.

Text-to-video concepts and social content

Product demos and cinematic storyboards

Image-to-video motion and creative iteration

Other models

Compare other models available through CometAPI for different quality, latency, capability and pricing trade-offs.

Open model comparison →

Flux

Flux 3

FLUX 3 - Real World Models: Towards Multimodal Flow Models as the Backbone of Visual Intelligence.

View model

Aliyun

Happy Horse 1.1

HappyHorse 1.1 is a multimodal video-generation model designed for professional content creation, advertising, short films, social media production, and storytelling. It extends the capabilities of HappyHorse 1.0—which gained significant attention after ranking highly in independent video-generation evaluations—with stronger scene coherence and improved visual fidelity.

View model

Bytedance

Seedance 2-0

Seedance 2.0 is ByteDance’s next-generation multimodal video foundation model focused on cinematic, multi-shot narrative video generation. Unlike single-shot text-to-video demos, Seedance 2.0 emphasizes reference-based control (images, short clips, audio), coherent character/style consistency across shots, and native audio/video synchronization — aiming to make AI video useful for professional creative and previsualization workflows.

View model

Google

Gemini omni fast

Gemini Omni Fast is a lightweight multimodal video generation model designed for fast and flexible content creation. It enables efficient video generation with support for multiple input types, making it suitable for interactive and iterative workflows.

View model

OpenAI

Sora 2 Pro

Sora 2 Pro is our most advanced and powerful media generation model, capable of generating videos with synchronized Audio. It can create detailed, dynamic video clips from natural language or images.

View model

Aliyun

Happy Horse 1.0

Happy Horse 1.0 — A high-quality audio-video generation model that supports text-to-video and image-to-video creation. It can generate synchronized visuals, audio, and lip movements, making it suitable for short films, advertising creatives, and product showcases.

View model

Uptime

Review live heartbeat data, endpoint availability and observed response times before moving into production.

Versions

Review available model identifiers before pinning a production integration.

wan3.0

Keep exploring

Compare models and continue your research

Aliyun

Available Popular

wan3.0

Wan3.0 API

Starting price

$0.05 / second

Usage-based billing

API health

Available

Production endpoint

Response

Async ready

Observed API response

Released

Aug 24, 2026

Aliyun

Playground

Try Wan3.0 with a real request, review its parameters and validate the output before integrating the API.

Overview

A practical overview of Wan3.0, including important behavior and integration considerations.

Technical Specifications of Wan 3.0

Specification	Wan 3.0
Model Type	Multimodal all-in-one video generation model
Model Status	Public API preview
Input Types	Text, image, video, audio, documents, web pages
Video Generation	Text-to-video, image-to-video, reference-to-video
Video Editing	Instruction-based and reference-based editing
Maximum Duration	30 seconds in a single generation
Output Resolution	480P, 720P, 1080P
Native Audio-Visual Generation	Yes
Reference Assets	Up to 20 multimodal reference assets
Document Inputs	DOC, XLS, PPT, PDF, TXT, KEY, PAGES, NUMBERS, MD
Maximum Document Size	100 MB
Maximum Document Pages	50 pages
API Access	Alibaba Cloud Model Studio API preview
API Generation Mode	Asynchronous
480P Price	$0.05/sec
720P Price	$0.10/sec
1080P Price	$0.20/sec

What Is Wan 3.0?

Wan 3.0 is Alibaba's next-generation multimodal video generation model designed to turn text, images, video, audio, documents, and web content into coherent video.

This makes Wan 3.0 less like a simple prompt-to-video generator and more like a multimodal creative production engine.

Main Features of Wan 3.0

Native 30-second video generation: Wan 3.0 can generate up to 30 seconds of video in a single pass, with intelligent duration selection and video extension capabilities.
Omni-Reference: Text, images, video and audio can be combined as references. Wan 3.0 also extends reference-based generation to documents and web pages.
Document-to-video: PPT, PDF, DOC, XLS, TXT, KEY, PAGES, NUMBERS and MD files can be used as creative inputs, allowing presentations, reports and structured information to become video content.
Native audiovisual generation: Wan 3.0 can generate video and sound together, supporting dialogue, environmental audio and music-oriented audio visual scenes.
Reference consistency: The model is designed to preserve characters, props, environments, spatial relationships and styles across reference-driven generations.
Video editing: Wan 3.0 supports modifications to generated visual content, plot and dialogue rather than requiring every iteration to start from scratch.

How Does Wan 3.0 Compare With Other Video Models?

Model	Native Duration	Image-to-Video	Reference Control	Audio	Document/Web Input	Main Strength
Wan 3.0	30s	✓	Strong	✓	✓	All-in-one multimodal production
Wan 2.7	15s	✓	✓	✓	Limited	Established Wan video workflows
Grok Imagine Video 1.5	Up to 15s	✓	✓	✓	—	Fast short-form creative video
Veo	Model-dependent	✓	✓	✓	Multimodal	Cinematic generation
Kling	Model-dependent	✓	✓	✓	—	Character and motion generation
Seedance	Model-dependent	✓	✓	✓	—	Creative and multi-shot video

The key differentiator is input breadth.

Representative Use Cases for Wan 3.0

1. AI filmmaking and story production

The 30-second single-generation capability makes Wan 3.0 useful for scenes requiring continuous camera movement, dialogue and multiple actions without stitching numerous short clips.

2. Product advertising

A product image or collection of references can be combined with a director-style prompt to create product demonstrations, UGC advertisements and cinematic brand videos.

3. Presentation-to-video generation

Wan 3.0 can process PPT, PDF, DOC, XLS and other supported document formats, making it suitable for converting reports, presentations and structured information into visual narratives.

4. Character-consistent video

Reference images, video and other media can be used to establish characters, objects and environments before generating a scene.

The 30-second duration and vertical 9:16 aspect ratio make Wan 3.0 suitable for short-form social content, advertisements and narrative clips.

6. Video editing and iteration

Wan 3.0 can modify existing generated content, including visual elements, story content and dialogue, enabling iterative creative workflows.

Wan 3.0 API Parameters

The official API uses an asynchronous video-generation endpoint. A simplified request contains a model, input, and parameters object.

Important parameters include:

Parameter	Description
model	wan3.0-video
input.prompt	Director-style generation instruction
input.media	Reference images, videos, audio, files or web resources
parameters.resolution	480P, 720P, 1080P
parameters.ratio	adaptive, 16:9, 4:3, 1:1, 3:4, 9:16
parameters.duration	2–30 seconds; -1 enables smart duration
parameters.audio	Whether to include an audio track
parameters.seed	Random seed for reproducibility
parameters.watermark	Whether to add a watermark

How to Use Wan 3.0 API on CometAPI

For developers using multiple AI video models, CometAPI can serve as a unified access layer for experimenting with Wan 3.0 alongside other video-generation models.

A typical workflow is:

Create or log in to a CometAPI account.
Obtain a CometAPI API key.
Select the Wan 3.0 model endpoint.
Submit a text-to-video, image-to-video, or reference-based generation request.
Specify resolution, duration, aspect ratio, and other supported parameters.
Monitor the asynchronous generation task.
Retrieve the generated video when processing completes.

FAQ

Pricing

Use the quick estimate above for a single run, then review the full CometAPI and official-price comparison.

5-second test

$0.25

Estimated CometAPI usage cost

10-second test

$0.5

Estimated CometAPI usage cost

15-second test

$0.75

Estimated CometAPI usage cost

Pricing for Wan3.0

Wan 3.0 Video Generation Pricing

From fast verification to cinematic output, billing is based on generated video duration and the selected resolution, turning every generation into a planned creative investment.

Customer-facing model: wan3.0

Output Resolution	Price per Generated Second	5-Second Video
480P	$0.05	$0.25
720P	$0.10	$0.50
1080P	$0.20	$1.00

Supported duration: 2–30 seconds
Billing unit: generated video second
Choose the appropriate output resolution for each generation
Final charge = applicable resolution price × successfully generated video duration

API

Copy a working endpoint and code example, then open the complete API reference when you need every parameter.

One API, production-ready model access

Authenticate once, call the model endpoint and keep the same billing and observability workflow across providers.

POST/v1/videosGET/v1/videos/{task_id}/contentGET/v1/videos/{task_id}

Sample code and API for Wan3.0

POST

/v1/videos

GET

/v1/videos/{task_id}/content

GET

/v1/videos/{task_id}

response=$(curl -sS --fail-with-body "https://api.cometapi.com/v1/videos" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F model=wan3.0 \
  -F prompt='A small robot walks through a bright greenhouse with smooth camera movement.' \
  -F seconds=5 \
  -F size=1920x1080) || exit 1

video_id=$(printf '%s' "$response" | sed -n 's/.*"id"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
if [ -z "$video_id" ]; then
  printf 'Missing video ID: %s
' "$response" >&2
  exit 1
fi
printf 'Video ID: %s
' "$video_id"

polls=0
while [ "$polls" -lt 54 ]; do
  status_response=$(curl -sS --fail-with-body "https://api.cometapi.com/v1/videos/${video_id}" \
    -H "Authorization: Bearer $COMETAPI_KEY") || exit 1
  progress=$(printf '%s' "$status_response" | sed -n 's/.*"progress"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
  status=$(printf '%s' "$status_response" | sed -n 's/.*"status"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
  printf 'Progress: %s, Status: %s
' "${progress:-0%}" "${status:-unknown}"
  case "$status" in
    FAILURE|failure|failed|error|cancelled|canceled) exit 1 ;;
    completed|succeeded|success) break ;;
  esac
  [ "$progress" = "100%" ] && break
  polls=$((polls + 1))
  sleep 10
done
if [ "$polls" -ge 54 ]; then
  echo "Video generation did not complete within 9 minutes" >&2
  exit 1
fi

mkdir -p output
output_path="output/${video_id}.mp4"
curl -sS --fail-with-body "https://api.cometapi.com/v1/videos/${video_id}/content" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -o "$output_path"
printf 'Saved: %s (%s bytes)
' "$output_path" "$(wc -c < "$output_path")"

cURL Code Example

response=$(curl -sS --fail-with-body "https://api.cometapi.com/v1/videos" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F model=wan3.0 \
  -F prompt='A small robot walks through a bright greenhouse with smooth camera movement.' \
  -F seconds=5 \
  -F size=1920x1080) || exit 1

video_id=$(printf '%s' "$response" | sed -n 's/.*"id"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
if [ -z "$video_id" ]; then
  printf 'Missing video ID: %s\n' "$response" >&2
  exit 1
fi
printf 'Video ID: %s\n' "$video_id"

polls=0
while [ "$polls" -lt 54 ]; do
  status_response=$(curl -sS --fail-with-body "https://api.cometapi.com/v1/videos/${video_id}" \
    -H "Authorization: Bearer $COMETAPI_KEY") || exit 1
  progress=$(printf '%s' "$status_response" | sed -n 's/.*"progress"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
  status=$(printf '%s' "$status_response" | sed -n 's/.*"status"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
  printf 'Progress: %s, Status: %s\n' "${progress:-0%}" "${status:-unknown}"
  case "$status" in
    FAILURE|failure|failed|error|cancelled|canceled) exit 1 ;;
    completed|succeeded|success) break ;;
  esac
  [ "$progress" = "100%" ] && break
  polls=$((polls + 1))
  sleep 10
done
if [ "$polls" -ge 54 ]; then
  echo "Video generation did not complete within 9 minutes" >&2
  exit 1
fi

mkdir -p output
output_path="output/${video_id}.mp4"
curl -sS --fail-with-body "https://api.cometapi.com/v1/videos/${video_id}/content" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -o "$output_path"
printf 'Saved: %s (%s bytes)\n' "$output_path" "$(wc -c < "$output_path")"

Python Code Example

import os
import time
from pathlib import Path

import requests

# Get your API key from https://www.cometapi.com/console/token, and paste it here
API_KEY = os.environ.get("COMETAPI_KEY") or "<YOUR_COMETAPI_KEY>"
BASE_URL = "https://api.cometapi.com".rstrip("/")

response = requests.post(
    f"{BASE_URL}/v1/videos",
    headers={"Authorization": f"Bearer {API_KEY}"},
    files={
        "model": (None, "wan3.0"),
        "prompt": (None, "A small robot walks through a bright greenhouse with smooth camera movement."),
        "seconds": (None, "5"),
        "size": (None, "1920x1080"),
    },
    timeout=120,
)
response.raise_for_status()
video_id = response.json()["id"]
print(f"Video ID: {video_id}")

deadline = time.monotonic() + 540
while time.monotonic() < deadline:
    response = requests.get(
        f"{BASE_URL}/v1/videos/{video_id}",
        headers={"Authorization": f"Bearer {API_KEY}"},
        timeout=120,
    )
    response.raise_for_status()
    result = response.json()
    data = result.get("data") or result
    progress = data.get("progress", result.get("progress", "0%"))
    status = str(data.get("status", result.get("status", "unknown")))
    print(f"Progress: {progress}, Status: {status}")
    if status.lower() in {"failure", "failed", "error", "cancelled", "canceled"}:
        raise RuntimeError(f"Video generation failed: {result}")
    if progress == "100%" or status.lower() in {"completed", "succeeded", "success"}:
        break
    time.sleep(10)
else:
    raise TimeoutError("Video generation did not complete within 9 minutes")

response = requests.get(
    f"{BASE_URL}/v1/videos/{video_id}/content",
    headers={"Authorization": f"Bearer {API_KEY}"},
    timeout=120,
)
response.raise_for_status()
output_path = Path("output") / f"{video_id}.mp4"
output_path.parent.mkdir(parents=True, exist_ok=True)
output_path.write_bytes(response.content)
print(f"Saved: {output_path} ({output_path.stat().st_size} bytes)")

JavaScript Code Example

import { mkdir, writeFile } from "node:fs/promises";

// Get your API key from https://www.cometapi.com/console/token, and paste it here
const apiKey = process.env["COMETAPI_KEY"] || "<YOUR_COMETAPI_KEY>";
const baseUrl = "https://api.cometapi.com".replace(/\/$/, "");

const form = new FormData();
form.append("model", "wan3.0");
form.append("prompt", "A small robot walks through a bright greenhouse with smooth camera movement.");
form.append("seconds", "5");
form.append("size", "1920x1080");

let response = await fetch(`${baseUrl}/v1/videos`, {
  method: "POST",
  headers: { Authorization: `Bearer ${apiKey}` },
  body: form,
});
if (!response.ok) throw new Error(await response.text());
const { id: videoId } = await response.json();
console.log(`Video ID: ${videoId}`);

const deadline = Date.now() + 540_000;
let completed = false;
while (Date.now() < deadline) {
  response = await fetch(`${baseUrl}/v1/videos/${videoId}`, {
    headers: { Authorization: `Bearer ${apiKey}` },
  });
  if (!response.ok) throw new Error(await response.text());
  const result = await response.json();
  const data = result.data || result;
  const progress = data.progress || result.progress || "0%";
  const status = String(data.status || result.status || "unknown");
  console.log(`Progress: ${progress}, Status: ${status}`);
  if (["failure", "failed", "error", "cancelled", "canceled"].includes(status.toLowerCase())) {
    throw new Error(`Video generation failed: ${JSON.stringify(result)}`);
  }
  if (progress === "100%" || ["completed", "succeeded", "success"].includes(status.toLowerCase())) {
    completed = true;
    break;
  }
  await new Promise((resolve) => setTimeout(resolve, 10_000));
}
if (!completed) throw new Error("Video generation did not complete within 9 minutes");

response = await fetch(`${baseUrl}/v1/videos/${videoId}/content`, {
  headers: { Authorization: `Bearer ${apiKey}` },
});
if (!response.ok) throw new Error(await response.text());
const video = Buffer.from(await response.arrayBuffer());
await mkdir("output", { recursive: true });
const outputPath = `output/${videoId}.mp4`;
await writeFile(outputPath, video);
console.log(`Saved: ${outputPath} (${video.length} bytes)`);

Capabilities

Scan the model facts that matter before you choose an architecture or estimate production workload.

Supported capabilities

Features returned by the existing model API.

text-to-video

image-to-video

Input and output

Inputs

text

Outputs

video

Production profile

Provider: Aliyun
Context: Model specific
Commercial use: Supported

Use cases

Use Wan3.0 for production workflows that match its video capabilities, then compare alternatives before committing to a long-term integration.

Text-to-video concepts and social content

Product demos and cinematic storyboards

Image-to-video motion and creative iteration

Other models

Compare other models available through CometAPI for different quality, latency, capability and pricing trade-offs.

Open model comparison →

Flux

Flux 3

FLUX 3 - Real World Models: Towards Multimodal Flow Models as the Backbone of Visual Intelligence.

Sora 2 Pro is our most advanced and powerful media generation model, capable of generating videos with synchronized Audio. It can create detailed, dynamic video clips from natural language or images.

Uptime

Review live heartbeat data, endpoint availability and observed response times before moving into production.

Versions

Review available model identifiers before pinning a production integration.

wan3.0

Keep exploring

Wan3.0 API

Playground

Overview

Technical Specifications of Wan 3.0

What Is Wan 3.0?

Main Features of Wan 3.0

How Does Wan 3.0 Compare With Other Video Models?

Representative Use Cases for Wan 3.0

1. AI filmmaking and story production

2. Product advertising

3. Presentation-to-video generation

4. Character-consistent video

5. Social media content

6. Video editing and iteration

Wan 3.0 API Parameters

How to Use Wan 3.0 API on CometAPI

FAQ

What is the official Wan 3.0 API model ID?

What makes Wan 3.0 different from Wan 2.7?

What resolutions does the Wan 3.0 API support?

Does Wan 3.0 generate audio together with video?

Can Wan 3.0 turn a PDF or PowerPoint into a video?

Can Wan 3.0 generate a 30-second video in one API call?

Can Wan 3.0 use multiple reference images, videos and audio files?

Pricing

Pricing for Wan3.0

Wan 3.0 Video Generation Pricing

API

One API, production-ready model access

Sample code and API for Wan3.0

cURL Code Example

Python Code Example

JavaScript Code Example

Capabilities

Use cases

Other models

Uptime

Versions

Compare models and continue your research

Wan3.0 API

Playground

Overview

Technical Specifications of Wan 3.0

What Is Wan 3.0?

Main Features of Wan 3.0

How Does Wan 3.0 Compare With Other Video Models?

Representative Use Cases for Wan 3.0

1. AI filmmaking and story production

2. Product advertising

3. Presentation-to-video generation

4. Character-consistent video

5. Social media content

6. Video editing and iteration

Wan 3.0 API Parameters

How to Use Wan 3.0 API on CometAPI

FAQ

What is the official Wan 3.0 API model ID?

What makes Wan 3.0 different from Wan 2.7?

What resolutions does the Wan 3.0 API support?

Does Wan 3.0 generate audio together with video?

Can Wan 3.0 turn a PDF or PowerPoint into a video?

Can Wan 3.0 generate a 30-second video in one API call?

Can Wan 3.0 use multiple reference images, videos and audio files?

Pricing

Pricing for Wan3.0

Wan 3.0 Video Generation Pricing

API

One API, production-ready model access

Sample code and API for Wan3.0

cURL Code Example

Python Code Example

JavaScript Code Example

Capabilities

Use cases

Other models

Uptime

Versions

Compare models and continue your research