What reference inputs does the Wan 3.0 API support?

Wan 3.0 supports multimodal reference workflows involving images, videos, audio, documents, and public webpages, in addition to text prompts. Supported combinations and individual media limits depend on the selected generation mode.

How can I control the opening and ending of a Wan 3.0 video?

Wan 3.0 supports first-frame and first/last-frame guidance. Providing suitable opening and ending images helps guide the composition and visual transition, although exact motion between the frames is not guaranteed.

Can Wan 3.0 generate video with dialogue and background music?

Yes. Wan 3.0 supports native audiovisual generation, including dialogue, background music, and sound effects. Audio quality and synchronization can vary, so review the generated result before publishing.

Should I choose Wan 3.0 or Wan 3.0 Prime for video generation?

Choose Wan 3.0 as the general-purpose option for multimodal video creation and editing. Choose Wan 3.0 Prime when generation speed is a priority, then compare output quality and latency on representative prompts.

What resolution and aspect ratios does the Wan 3.0 API support?

The official model documentation lists 480p, 720p, and 1080p output, with adaptive, 16:9, 21:9, 4:3, 1:1, 3:4, and 9:16 aspect ratios. Confirm which options are exposed by your CometAPI endpoint.

Can the Wan 3.0 API generate a 30-second video from a single prompt?

Yes. Wan 3.0 supports single-generation videos up to 30 seconds at 30 fps. The exact duration and request fields available through CometAPI should be confirmed in its current API schema.

How do I retrieve a generated video from the CometAPI Wan 3.0 endpoint?

Submit a request to CometAPI's POST /v1/videos endpoint using model ID `wan3.0`, retain the returned task or video ID, poll the documented status endpoint, and retrieve the completed video using the corresponding content endpoint.

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

$0.04 / 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.

Pricing

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

5-second test

$0.2000

Estimated CometAPI usage cost

10-second test

$0.4000

Estimated CometAPI usage cost

15-second test

$0.6000

Estimated CometAPI usage cost

Minimum charge transparency This prototype does not assume a hidden per-request minimum. If a production billing floor or minimum top-up applies, it must be displayed before purchase and included in every budget estimate.

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

Model brief

A stable model identity for search and evaluation, paired with live catalog data that can change without rewriting the page's core SEO structure.

Stable identity

What is Wan3.0?

Canonical model identity stays stable as pricing and limits change.

Live model data

Current catalog snapshot

Availability

Available

Starting price

$0.04 / second

Context

See capabilities

Catalog date

Aug 24, 2026

Overview

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

Technical specifications of Wan 3.0

Item	Specification
Model name	Wan 3.0
CometAPI Model ID	wan3.0
Original provider	Alibaba Cloud (Aliyun)
Model category	All-in-One AI video generation
Input	Text prompt; supported image, video, audio, document and public webpage references
Output	Generated video
Supported tasks	Text-to-video, image-to-video, reference-based generation, video editing and extension
Resolution	480p, 720p, 1080p
Video duration	2–30 seconds in the official API specification
Frame rate	30 fps
Aspect ratios	Adaptive, 16:9, 21:9, 4:3, 1:1, 3:4, 9:16
Audio	Native dialogue, background music and sound effects; audio can be disabled in supported workflows
Reference capacity	Up to 20 multimodal reference assets per request at the model-guide level, subject to input-combination rules
API endpoint	CometAPI POST /v1/videos
Generation workflow	Asynchronous task submission, status polling and video retrieval
Context window	No conventional text-token context window published for this video model

CometAPI identifies the model as wan3.0 and documents its video API at /v1/videos. The technical capabilities above are based on the provider's Wan 3.0 documentation; gateway-specific parameter support should be verified against CometAPI's current API reference.

Wan3.0

CometAPI

What is Wan 3.0?

Wan 3.0 is an all-in-one AI video-generation model developed by Alibaba Cloud. It transforms written prompts and supported reference materials into audiovisual content, with a focus on longer scenes, multimodal creative control, and integrated video editing.

Unlike video models limited to text prompts or a single reference image, Wan 3.0 supports workflows involving first and last frames, reference videos, audio, documents, and public webpages. This makes it useful for producing product demonstrations, cinematic concepts, marketing videos, and reference-driven storytelling through a unified generation model.

Wan3.0

Alibaba Cloud Model Studio

Main features of Wan 3.0

30-second video generation: Create clips up to 30 seconds long in a single generation, allowing more room for continuous actions and narrative development.
Multimodal reference inputs: Use supported images, videos, audio, documents, and public webpage content to provide creative context.
Native audio-video generation: Generate dialogue, background music, and sound effects alongside the video.
First-frame and last-frame control: Guide the beginning and ending compositions to make scene transitions more predictable.
Video editing and extension: Use supported editing workflows to modify existing footage or continue a scene.
Flexible visual output: Choose 480p, 720p, or 1080p output and supported aspect ratios for different content formats.

These capabilities are documented in Alibaba Cloud's Wan 3.0 model guide. Actual input combinations and limits depend on the selected task and API schema.

Wan3.0

Alibaba Cloud Model Studio

Benchmark performance of Wan 3.0

Wan 3.0's documented strengths are its 30-second generation capability, native audio-video output, multimodal references, and integrated editing workflows. The official materials reviewed for this page do not provide a standardized numerical benchmark score that supports a reliable cross-model ranking.

For production evaluation, test Wan 3.0 on a fixed set of representative prompts and reference assets. Measure prompt adherence, motion continuity, character consistency, audiovisual synchronization, successful generation rate, and end-to-end latency. These are recommended evaluation criteria, not claimed benchmark results.

Wan 3.0 vs. Wan 3.0 Prime vs. Wan 2.7

Model	Key distinction	Recommended use
Wan 3.0 (wan3.0)	General-purpose all-in-one video generation with multimodal references and editing	Longer creative sequences, reference-driven videos and audiovisual content
Wan 3.0 Prime (wan3.0-prime)	Speed-optimized variant of Wan 3.0	Workflows where generation speed is a priority
Wan 2.7	Earlier model family with its own generation and editing endpoints	Existing applications tied to Wan 2.7 workflows or requirements

Wan 3.0 and Prime share the same core capability direction, while Prime is positioned as the faster version. A fair comparison should measure quality and latency under equivalent settings instead of assuming that one version always produces better results.

Wan3.0

阿里云帮助中心

Representative use cases

Product advertising: Turn product descriptions and reference images into cinematic demonstrations.
Social media content: Produce vertical or square video clips for short-form campaigns.
Storyboard development: Convert scene descriptions into moving visual concepts before full production.
Reference-driven storytelling: Use visual references and opening/closing frames to guide a scene.
Document-to-video workflows: Transform supported documents or public webpage content into video concepts.
Video editing and continuation: Revise or extend existing footage through supported model operations.

Limitations and implementation notes

Generation is not deterministic: Identical prompts may produce different motion, composition, or audio details across runs.
Reference inputs have constraints: Different reference types cannot necessarily be combined in one request. Validate supported combinations before submitting jobs.
Text and fine details require review: Inspect generated text, logos, small objects, hands, and fast-moving scenes for artifacts.
Audio quality varies: Native audio generation does not guarantee perfect dialogue clarity or synchronization in every output.
Generation is asynchronous: Applications should track task status and handle failed or delayed jobs instead of assuming an immediate video response.
Gateway parameters may differ: Alibaba Cloud's API and CometAPI's API are separate interfaces. Use CometAPI's model ID and request schema when integrating through CometAPI.

How to access the Wan 3.0 API through CometAPI

The CometAPI catalog lists the model identifier as wan3.0 and documents the video-generation endpoint as POST /v1/videos. Its interface also provides task-status and video-content retrieval endpoints

Typical integration flow:

Configure your CometAPI API key.
Submit a video-generation request using model=wan3.0 and your prompt.
Save the returned task or video ID.
Poll the task-status endpoint until generation finishes.
Retrieve the completed video through the documented content endpoint.

FAQ

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.

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.

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

video-editing

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 →

Aliyun

Wan 3.0 Prime

Wan 3.0 Prime is Alibaba Cloud Model Studio's speed-optimized version of the Wan 3.0 video-generation model.

View model

Aliyun

Wan2.7

Wan2.7 is a video generation model designed for high-quality visual synthesis and improved motion consistency. It is suitable for cinematic content creation and professional video production workflows.

View model

Aliyun

Wan2.6

Wan2.6 is a video generation model designed for stable and efficient video synthesis. It provides reliable visual quality and smooth motion generation for general video creation tasks.

View model

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

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

wan3.0-prime

Updates

Follow meaningful availability, pricing and capability changes for Wan3.0 without losing the stable model page.

Model changelog

One page that gets stronger over time.

Release notes, pricing changes, benchmark updates and migration guidance accumulate here while the canonical URL stays unchanged.

Aug 24, 2026

API availability confirmed

Wan3.0 is available through the CometAPI model catalog and API documentation.

Current

Live data

Pricing and limits synced from the catalog

Price, context, availability and limits are treated as dynamic properties instead of being embedded in the page title or model identity.

Aug 6, 2026

Permanent model entity created

The provider and model slug form a durable canonical URL; future content and data updates remain on this page.

Keep exploring

Compare models and continue your research

Aliyun

Available Popular

wan3.0

Wan3.0 API

Starting price

$0.04 / 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.

Pricing

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

5-second test

$0.2000

Estimated CometAPI usage cost

10-second test

$0.4000

Estimated CometAPI usage cost

15-second test

$0.6000

Estimated CometAPI usage cost

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

Model brief

A stable model identity for search and evaluation, paired with live catalog data that can change without rewriting the page's core SEO structure.

Stable identity

What is Wan3.0?

Canonical model identity stays stable as pricing and limits change.

Live model data

Current catalog snapshot

Availability

Available

Starting price

$0.04 / second

Context

See capabilities

Catalog date

Aug 24, 2026

Overview

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

Technical specifications of Wan 3.0

Item	Specification
Model name	Wan 3.0
CometAPI Model ID	wan3.0
Original provider	Alibaba Cloud (Aliyun)
Model category	All-in-One AI video generation
Input	Text prompt; supported image, video, audio, document and public webpage references
Output	Generated video
Supported tasks	Text-to-video, image-to-video, reference-based generation, video editing and extension
Resolution	480p, 720p, 1080p
Video duration	2–30 seconds in the official API specification
Frame rate	30 fps
Aspect ratios	Adaptive, 16:9, 21:9, 4:3, 1:1, 3:4, 9:16
Audio	Native dialogue, background music and sound effects; audio can be disabled in supported workflows
Reference capacity	Up to 20 multimodal reference assets per request at the model-guide level, subject to input-combination rules
API endpoint	CometAPI POST /v1/videos
Generation workflow	Asynchronous task submission, status polling and video retrieval
Context window	No conventional text-token context window published for this video model

Wan3.0

CometAPI

What is Wan 3.0?

Wan3.0

Alibaba Cloud Model Studio

Main features of Wan 3.0

30-second video generation: Create clips up to 30 seconds long in a single generation, allowing more room for continuous actions and narrative development.
Multimodal reference inputs: Use supported images, videos, audio, documents, and public webpage content to provide creative context.
Native audio-video generation: Generate dialogue, background music, and sound effects alongside the video.
First-frame and last-frame control: Guide the beginning and ending compositions to make scene transitions more predictable.
Video editing and extension: Use supported editing workflows to modify existing footage or continue a scene.
Flexible visual output: Choose 480p, 720p, or 1080p output and supported aspect ratios for different content formats.

These capabilities are documented in Alibaba Cloud's Wan 3.0 model guide. Actual input combinations and limits depend on the selected task and API schema.

Wan3.0

Alibaba Cloud Model Studio

Benchmark performance of Wan 3.0

Wan 3.0 vs. Wan 3.0 Prime vs. Wan 2.7

Model	Key distinction	Recommended use
Wan 3.0 (wan3.0)	General-purpose all-in-one video generation with multimodal references and editing	Longer creative sequences, reference-driven videos and audiovisual content
Wan 3.0 Prime (wan3.0-prime)	Speed-optimized variant of Wan 3.0	Workflows where generation speed is a priority
Wan 2.7	Earlier model family with its own generation and editing endpoints	Existing applications tied to Wan 2.7 workflows or requirements

Wan3.0

阿里云帮助中心

Representative use cases

Product advertising: Turn product descriptions and reference images into cinematic demonstrations.
Social media content: Produce vertical or square video clips for short-form campaigns.
Storyboard development: Convert scene descriptions into moving visual concepts before full production.
Reference-driven storytelling: Use visual references and opening/closing frames to guide a scene.
Document-to-video workflows: Transform supported documents or public webpage content into video concepts.
Video editing and continuation: Revise or extend existing footage through supported model operations.

Limitations and implementation notes

Generation is not deterministic: Identical prompts may produce different motion, composition, or audio details across runs.
Reference inputs have constraints: Different reference types cannot necessarily be combined in one request. Validate supported combinations before submitting jobs.
Text and fine details require review: Inspect generated text, logos, small objects, hands, and fast-moving scenes for artifacts.
Audio quality varies: Native audio generation does not guarantee perfect dialogue clarity or synchronization in every output.
Generation is asynchronous: Applications should track task status and handle failed or delayed jobs instead of assuming an immediate video response.
Gateway parameters may differ: Alibaba Cloud's API and CometAPI's API are separate interfaces. Use CometAPI's model ID and request schema when integrating through CometAPI.

How to access the Wan 3.0 API through CometAPI

Typical integration flow:

Configure your CometAPI API key.
Submit a video-generation request using model=wan3.0 and your prompt.
Save the returned task or video ID.
Poll the task-status endpoint until generation finishes.
Retrieve the completed video through the documented content endpoint.

FAQ

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.

Sample code and API for Wan3.0

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

video-editing

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 →

Aliyun

Wan 3.0 Prime

Wan 3.0 Prime is Alibaba Cloud Model Studio's speed-optimized version of the Wan 3.0 video-generation model.

Wan2.6 is a video generation model designed for stable and efficient video synthesis. It provides reliable visual quality and smooth motion generation for general video creation tasks.

View model

Flux

Flux 3

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

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

wan3.0-prime

Updates

Follow meaningful availability, pricing and capability changes for Wan3.0 without losing the stable model page.

Model changelog

One page that gets stronger over time.

Release notes, pricing changes, benchmark updates and migration guidance accumulate here while the canonical URL stays unchanged.

Aug 24, 2026

API availability confirmed

Wan3.0 is available through the CometAPI model catalog and API documentation.

Current

Live data

Pricing and limits synced from the catalog

Price, context, availability and limits are treated as dynamic properties instead of being embedded in the page title or model identity.

Aug 6, 2026

Permanent model entity created

The provider and model slug form a durable canonical URL; future content and data updates remain on this page.

Keep exploring