What are the main limitations of the Vidu Q3 API?

A single generation is limited to 16 seconds, so longer productions require multiple clips and post-production editing to create extended narratives.

What resolutions are available in the Vidu Q3 API?

The model supports 540p, 720p, and 1080p video generation at 24 FPS.

When should I choose Vidu Q3 instead of Vidu Q3 Turbo?

Choose Vidu Q3 when output quality, narrative consistency, and cinematic storytelling are more important than generation speed. Q3 Turbo is optimized for faster iteration.

Does the Vidu Q3 API support image-to-video generation?

Yes. Vidu Q3 supports image-to-video workflows that animate still images into motion sequences while preserving visual identity and scene consistency.

What is the maximum video length supported by Vidu Q3 API?

Vidu Q3 supports video durations from 1 to 16 seconds per generation while maintaining audio-video synchronization throughout the clip.

Can the Vidu Q3 API generate dialogue, music, and video together?

Yes. Vidu Q3 natively generates video, dialogue, narration, sound effects, and background music in a synchronized output, eliminating the need for separate audio production.

Is Vidu Q3 suitable for AI short films and narrative advertising?

Yes. Vidu Q3 was specifically designed for story-driven content such as short dramas, cinematic scenes, narrative advertisements, and comic-style productions.

Can Vidu Q3 create multi-character conversations with synchronized speech?

Yes. One of Vidu Q3's key capabilities is support for multi-speaker dialogue generation with synchronized audio and visual output.

Vidu

Available

viduq3

Vidu Q3 API

Vidu Q3 is a video generation model designed for high-quality content creation with strong visual realism and prompt adherence. It is suitable for creative video production and storytelling applications.

Starting price

$60.00 / 1M input tokens

Usage-based billing

API health

Available

Production endpoint

Response

Async ready

Observed API response

Released

Jun 1, 2026

Vidu

Pricing

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

First request

$0.1200

Estimated CometAPI usage cost

Ten requests

$1.20

Estimated CometAPI usage cost

Fifteen requests

$1.80

Estimated CometAPI usage cost

⇌

Credits conversion

1,000 credits = $1

Credits make budgets comparable across token, request and runtime billing. The USD amount remains the source of truth at checkout.

✓Current model in credits

Input

60,000

credits / 1M tokens

Output

60,000

credits / 1M tokens

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.

Vidu Video Generation Pricing

Pricing (Per Second)

Model	360p	540p	720p	1080p
`viduq3`	$0.056	$0.056	$0.1232	$0.1232
`viduq3-turbo`	$0.028	$0.028	$0.0616	$0.0616

💡 Billed per second. Total cost = price per second × video duration (seconds).

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 Vidu Q3?

Canonical model identity stays stable as pricing and limits change.

Live model data

Current catalog snapshot

Availability

Available

Starting price

$60.00 / 1M input tokens

Context

See capabilities

Catalog date

Jun 1, 2026

Overview

A practical overview of Vidu Q3, including important behavior and integration considerations.

Technical Specifications of Vidu Q3

Item	Vidu Q3 (viduq3-pro)
Model ID	viduq3-pro
Provider	Vidu
Model Family	Vidu Q3 Series
Model Type	AI Video Generation
Input Types	Text, Image, Start Image + End Image
Output Type	Video with native synchronized audio
Resolution	540p, 720p, 1080p
Duration	1–16 seconds
Frame Rate	24 FPS
Audio Generation	Native audio-video generation
Text-to-Video	Supported
Image-to-Video	Supported
Start-End-to-Video	Supported
Intelligent Shot Switching	Supported
Primary Focus	Narrative storytelling and cinematic video creation

What is Vidu Q3?

Vidu Q3 is Vidu's flagship third-generation video model built specifically for story-driven video generation. Unlike traditional AI video systems that generate visuals first and audio later, Vidu Q3 creates dialogue, narration, sound effects, music, and video simultaneously, enabling synchronized storytelling directly from a single generation workflow. The model is designed for short dramas, cinematic sequences, advertising content, and character-driven narratives.

Main Features of Vidu Q3

Native audio-video synchronization: Generates dialogue, narration, sound effects, and music directly alongside video.
16-second continuous generation: Produces complete narrative clips in a single generation run.
Frame-accurate camera control: Supports detailed control over camera movement, pacing, and scene composition.
Multi-speaker dialogue support: Designed for conversations and character interactions.
Multilingual generation: Supports English, Japanese, and Chinese content generation.
Cinematic storytelling optimization: Tuned specifically for drama, film-style content, comics, and narrative advertising.

Benchmark Performance of Vidu Q3

Unlike language models, Vidu Q3 does not publish standardized benchmark scores such as MMLU or SWE-Bench. Publicly disclosed performance indicators include:

Metric	Public Information
Maximum Duration	16 seconds
Maximum Resolution	1080p
Native Audio Generation	Yes
Multi-Speaker Dialogue	Yes
Multilingual Support	English, Japanese, Chinese
Frame-Level Camera Control	Yes

Artificial Analysis score of 1241 and ranking among leading global video-generation systems, although independent benchmark validation remains limited.

Vidu Q3 vs Vidu Q3 Turbo vs Kling 2.1

Feature	Vidu Q3	Vidu Q3 Turbo	Kling 2.1
Positioning	Premium quality	Speed optimized	General video generation
Native Audio	Yes	Yes	Workflow dependent
Max Duration	16s	16s	Varies
Resolution	Up to 1080p	Up to 1080p	Up to 1080p
Camera Control	Advanced	Advanced	Strong
Narrative Focus	Highest	Moderate	Strong
Generation Speed	Standard	Faster	Competitive

Known Limitations

Individual clips remain limited to 16 seconds.
Long-form productions require combining multiple generations.
Public benchmark transparency remains limited compared with leading LLM providers.
Narrative quality depends heavily on prompt design and scene planning.

Representative Use Cases

AI Short Films

Generate cinematic scenes with synchronized speech, ambient sound, and music.

Short Drama Production

Create serialized drama content without separate audio-production workflows.

Advertising and Brand Storytelling

Produce narrative commercials with integrated voiceover and sound design.

Comic and Manga Adaptation

Transform storyboards and illustrations into animated narrative clips.

Generate TikTok, Shorts, and Reels content with ready-to-publish synchronized audio.

Model Version Notes

Vidu Q3 represents the premium version of the Q3 family. Compared with Vidu Q3 Turbo, the standard Q3 model prioritizes output quality, narrative consistency, and cinematic storytelling rather than generation speed. Both models support native audio-video output and up to 16-second video generation.

How to Access and Deploy the viduq3 API on CometAPI

Create your CometAPI account or sign in to an existing account to access the API once it becomes available . After release, you will be able to obtain a HappyHorse-1.0 API key from the platform and be ready for testing or integration.

Step 2: Test the viduq3 API for Free in the Playground

Before deployment, you can try out the viduq3 API directly in the CometAPI playground. This provides an easy way to explore output quality, test hints, or image inputs, and gain a clearer understanding of the API's performance before using it in production.

Step 3: Deploy the viduq3 API in Production

After testing, the next step is to deploy the viduq3 API to your own application, product, or internal environment. This allows you to use the viduq3 API in real-world video generation scenarios where stable access and practical integration are crucial.

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.

POST/v1/videos

Sample code and API for Vidu Q3

Access comprehensive sample code and API resources for Vidu Q3 to streamline your integration process. Our detailed documentation provides step-by-step guidance, helping you leverage the full potential of Vidu Q3 in your projects.

POST

/v1/videos

# Create a video with viduq3
# Step 1: Submit the video generation request
echo "Submitting video generation request..."
response=$(curl -s https://api.cometapi.com/v1/videos \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F "model=viduq3" \
  -F "prompt=Ultra-realistic cinematic shot of an astronaut walking slowly through soft fog, volumetric light in light blue and pale amber tones, shallow depth of field, 35mm film texture, graceful camera movement." \
  -F "seconds=1" \
  -F "size=960x528")

echo "Response: $response"

# Extract video_id from response (handle JSON with spaces like "id": "xxx")
video_id=$(echo "$response" | tr -d '
' | sed 's/.*"id"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/')
echo "Video ID: $video_id"

# Step 2: Poll for progress until 100%
echo ""
echo "Checking video generation progress..."
while true; do
  status_response=$(curl -s "https://api.cometapi.com/v1/videos/$video_id" \
    -H "Authorization: Bearer $COMETAPI_KEY")

  progress=$(echo "$status_response" | grep -o '"progress"[[:space:]]*:[[:space:]]*"\?[^",}]*"\?' | head -1 | sed 's/.*:[[:space:]]*"\?//;s/"$//')
  status=$(echo "$status_response" | grep -o '"status"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1 | sed 's/.*"status"[[:space:]]*:[[:space:]]*"//;s/"$//')

  echo "Progress: $progress, Status: $status"

  if [ "$status" = "FAILURE" ] || [ "$status" = "failed" ] || [ "$status" = "error" ]; then
    echo "Video generation failed!"
    exit 1
  fi

  if [ "$progress" = "100%" ] || [ "$progress" = "100" ] || [ "$status" = "completed" ] || [ "$status" = "success" ]; then
    echo "Video generation completed!"
    break
  fi

  sleep 10
done

# Step 3: Download the video to output directory
echo ""
echo "Downloading video to ./output/$video_id.mp4..."
mkdir -p ./output
curl -s "https://api.cometapi.com/v1/videos/$video_id/content" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -o "./output/$video_id.mp4"

if [ -f "./output/$video_id.mp4" ]; then
  echo "Video saved to ./output/$video_id.mp4"
  ls -la "./output/$video_id.mp4"
else
  echo "Failed to download video"
  exit 1
fi

cURL Code Example

# Create a video with viduq3
# Step 1: Submit the video generation request
echo "Submitting video generation request..."
response=$(curl -s https://api.cometapi.com/v1/videos \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F "model=viduq3" \
  -F "prompt=Ultra-realistic cinematic shot of an astronaut walking slowly through soft fog, volumetric light in light blue and pale amber tones, shallow depth of field, 35mm film texture, graceful camera movement." \
  -F "seconds=1" \
  -F "size=960x528")

echo "Response: $response"

# Extract video_id from response (handle JSON with spaces like "id": "xxx")
video_id=$(echo "$response" | tr -d '\n' | sed 's/.*"id"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/')
echo "Video ID: $video_id"

# Step 2: Poll for progress until 100%
echo ""
echo "Checking video generation progress..."
while true; do
  status_response=$(curl -s "https://api.cometapi.com/v1/videos/$video_id" \
    -H "Authorization: Bearer $COMETAPI_KEY")
  
  progress=$(echo "$status_response" | grep -o '"progress"[[:space:]]*:[[:space:]]*"\?[^",}]*"\?' | head -1 | sed 's/.*:[[:space:]]*"\?//;s/"$//')
  status=$(echo "$status_response" | grep -o '"status"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1 | sed 's/.*"status"[[:space:]]*:[[:space:]]*"//;s/"$//')
  
  echo "Progress: $progress, Status: $status"
  
  if [ "$status" = "FAILURE" ] || [ "$status" = "failed" ] || [ "$status" = "error" ]; then
    echo "Video generation failed!"
    exit 1
  fi
  
  if [ "$progress" = "100%" ] || [ "$progress" = "100" ] || [ "$status" = "completed" ] || [ "$status" = "success" ]; then
    echo "Video generation completed!"
    break
  fi
  
  sleep 10
done

# Step 3: Download the video to output directory
echo ""
echo "Downloading video to ./output/$video_id.mp4..."
mkdir -p ./output
curl -s "https://api.cometapi.com/v1/videos/$video_id/content" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -o "./output/$video_id.mp4"

if [ -f "./output/$video_id.mp4" ]; then
  echo "Video saved to ./output/$video_id.mp4"
  ls -la "./output/$video_id.mp4"
else
  echo "Failed to download video"
  exit 1
fi

Python Code Example

# Create a video with viduq3 using raw HTTP requests
import os
import time
import requests

api_key = os.environ.get("COMETAPI_KEY")
base_url = "https://api.cometapi.com/v1"
headers = {"Authorization": f"Bearer {api_key}"}

# Step 1: Submit the video generation request
print("Submitting video generation request...")
response = requests.post(
    f"{base_url}/videos",
    headers=headers,
    files={
        "model": (None, "viduq3"),
        "prompt": (None, "Ultra-realistic cinematic shot of an astronaut walking slowly through soft fog, volumetric light in light blue and pale amber tones, shallow depth of field, 35mm film texture, graceful camera movement."),
        "seconds": (None, "1"),
        "size": (None, "960x528"),
    },
)

result = response.json()
print(f"Response: {result}")

video_id = result.get("id") or result.get("task_id")
print(f"Video ID: {video_id}")

# Step 2: Poll for progress until 100%
print("\nChecking video generation progress...")
while True:
    try:
        status_response = requests.get(f"{base_url}/videos/{video_id}", headers=headers)
        status_result = status_response.json()

        data = status_result.get("data") or status_result
        progress = data.get("progress", "0%")
        status = data.get("status", "unknown")

        print(f"Progress: {progress}, Status: {status}")

        if status in ["FAILURE", "failed", "error"]:
            print("Video generation failed!")
            print(status_result)
            exit(1)

        if progress == "100%" or progress == 100 or status in ["completed", "success"]:
            print("Video generation completed!")
            break
    except Exception as e:
        print(f"Temporary error: {e}, retrying...")

    time.sleep(10)

# Step 3: Download the video to output directory
print(f"\nDownloading video to ./output/{video_id}.mp4...")
os.makedirs("./output", exist_ok=True)

video_response = requests.get(f"{base_url}/videos/{video_id}/content", headers=headers)

output_path = f"./output/{video_id}.mp4"
with open(output_path, "wb") as f:
    f.write(video_response.content)

if os.path.exists(output_path):
    file_size = os.path.getsize(output_path)
    print(f"Video saved to {output_path}")
    print(f"File size: {file_size} bytes")
else:
    print("Failed to download video")
    exit(1)

JavaScript Code Example

// Create a video with viduq3 using raw HTTP requests
import fs from "fs";
import path from "path";

const apiKey = process.env.COMETAPI_KEY;
const baseUrl = "https://api.cometapi.com/v1";
const headers = { Authorization: `Bearer ${apiKey}` };

function sleep(ms) {
  return new Promise((resolve) => setTimeout(resolve, ms));
}

// Step 1: Submit the video generation request
console.log("Submitting video generation request...");
const formData = new FormData();
formData.append("model", "viduq3");
formData.append("prompt", "Ultra-realistic cinematic shot of an astronaut walking slowly through soft fog, volumetric light in light blue and pale amber tones, shallow depth of field, 35mm film texture, graceful camera movement.");
formData.append("seconds", "1");
formData.append("size", "960x528");

const submitResponse = await fetch(`${baseUrl}/videos`, {
  method: "POST",
  headers,
  body: formData,
});

const result = await submitResponse.json();
console.log("Response:", JSON.stringify(result, null, 2));

const videoId = result.id || result.task_id;
console.log("Video ID:", videoId);

// Step 2: Poll for progress until 100%
console.log("\nChecking video generation progress...");
while (true) {
  try {
    const statusResponse = await fetch(`${baseUrl}/videos/${videoId}`, { headers });
    const statusResult = await statusResponse.json();
    const data = statusResult.data || statusResult;
    const progress = data.progress || "0%";
    const status = data.status || "unknown";

    console.log(`Progress: ${progress}, Status: ${status}`);

    if (status === "FAILURE" || status === "failed" || status === "error") {
      console.log("Video generation failed!");
      console.log(JSON.stringify(statusResult, null, 2));
      process.exit(1);
    }

    if (progress === "100%" || progress === 100 || status === "completed" || status === "success") {
      console.log("Video generation completed!");
      break;
    }
  } catch (e) {
    console.log(`Temporary error: ${e.message}, retrying...`);
  }

  await sleep(10000);
}

// Step 3: Download the video to output directory
console.log(`\nDownloading video to ./output/${videoId}.mp4...`);
fs.mkdirSync("./output", { recursive: true });

const videoResponse = await fetch(`${baseUrl}/videos/${videoId}/content`, { headers });
const outputPath = path.join("./output", `${videoId}.mp4`);
fs.writeFileSync(outputPath, Buffer.from(await videoResponse.arrayBuffer()));

if (fs.existsSync(outputPath)) {
  const stats = fs.statSync(outputPath);
  console.log(`Video saved to ${outputPath}`);
  console.log(`File size: ${stats.size} bytes`);
} else {
  console.log("Failed to download video");
  process.exit(1);
}

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: Vidu
Context: Model specific
Commercial use: Supported

Use cases

Use Vidu Q3 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

Wan3.0

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

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

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

Uptime

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

Uptime

Request success rate over the last 30 days, reflecting the reliability of each model provider. CometAPI monitors all connected providers in real time, 24/7.

Respond

302428msAvg. Response

Uptime

57.1%Avg. Uptime

Versions

Review available model identifiers before pinning a production integration.

viduq3-pro

viduq3-turbo

Updates

Follow meaningful availability, pricing and capability changes for Vidu Q3 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.

Jun 1, 2026

API availability confirmed

Vidu Q3 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.

Jun 1, 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

Vidu

Available

viduq3

Vidu Q3 API

Starting price

$60.00 / 1M input tokens

Usage-based billing

API health

Available

Production endpoint

Response

Async ready

Observed API response

Released

Jun 1, 2026

Vidu

Pricing

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

First request

$0.1200

Estimated CometAPI usage cost

Ten requests

$1.20

Estimated CometAPI usage cost

Fifteen requests

$1.80

Estimated CometAPI usage cost

⇌

Credits conversion

1,000 credits = $1

Credits make budgets comparable across token, request and runtime billing. The USD amount remains the source of truth at checkout.

✓Current model in credits

Input

60,000

credits / 1M tokens

Output

60,000

credits / 1M tokens

Vidu Video Generation Pricing

Pricing (Per Second)

Model	360p	540p	720p	1080p
`viduq3`	$0.056	$0.056	$0.1232	$0.1232
`viduq3-turbo`	$0.028	$0.028	$0.0616	$0.0616

💡 Billed per second. Total cost = price per second × video duration (seconds).

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 Vidu Q3?

Canonical model identity stays stable as pricing and limits change.

Live model data

Current catalog snapshot

Availability

Available

Starting price

$60.00 / 1M input tokens

Context

See capabilities

Catalog date

Jun 1, 2026

Overview

A practical overview of Vidu Q3, including important behavior and integration considerations.

Technical Specifications of Vidu Q3

Item	Vidu Q3 (viduq3-pro)
Model ID	viduq3-pro
Provider	Vidu
Model Family	Vidu Q3 Series
Model Type	AI Video Generation
Input Types	Text, Image, Start Image + End Image
Output Type	Video with native synchronized audio
Resolution	540p, 720p, 1080p
Duration	1–16 seconds
Frame Rate	24 FPS
Audio Generation	Native audio-video generation
Text-to-Video	Supported
Image-to-Video	Supported
Start-End-to-Video	Supported
Intelligent Shot Switching	Supported
Primary Focus	Narrative storytelling and cinematic video creation

What is Vidu Q3?

Main Features of Vidu Q3

Native audio-video synchronization: Generates dialogue, narration, sound effects, and music directly alongside video.
16-second continuous generation: Produces complete narrative clips in a single generation run.
Frame-accurate camera control: Supports detailed control over camera movement, pacing, and scene composition.
Multi-speaker dialogue support: Designed for conversations and character interactions.
Multilingual generation: Supports English, Japanese, and Chinese content generation.
Cinematic storytelling optimization: Tuned specifically for drama, film-style content, comics, and narrative advertising.

Benchmark Performance of Vidu Q3

Unlike language models, Vidu Q3 does not publish standardized benchmark scores such as MMLU or SWE-Bench. Publicly disclosed performance indicators include:

Metric	Public Information
Maximum Duration	16 seconds
Maximum Resolution	1080p
Native Audio Generation	Yes
Multi-Speaker Dialogue	Yes
Multilingual Support	English, Japanese, Chinese
Frame-Level Camera Control	Yes

Artificial Analysis score of 1241 and ranking among leading global video-generation systems, although independent benchmark validation remains limited.

Vidu Q3 vs Vidu Q3 Turbo vs Kling 2.1

Feature	Vidu Q3	Vidu Q3 Turbo	Kling 2.1
Positioning	Premium quality	Speed optimized	General video generation
Native Audio	Yes	Yes	Workflow dependent
Max Duration	16s	16s	Varies
Resolution	Up to 1080p	Up to 1080p	Up to 1080p
Camera Control	Advanced	Advanced	Strong
Narrative Focus	Highest	Moderate	Strong
Generation Speed	Standard	Faster	Competitive

Known Limitations

Individual clips remain limited to 16 seconds.
Long-form productions require combining multiple generations.
Public benchmark transparency remains limited compared with leading LLM providers.
Narrative quality depends heavily on prompt design and scene planning.

Representative Use Cases

AI Short Films

Generate cinematic scenes with synchronized speech, ambient sound, and music.

Short Drama Production

Create serialized drama content without separate audio-production workflows.

Advertising and Brand Storytelling

Produce narrative commercials with integrated voiceover and sound design.

Comic and Manga Adaptation

Transform storyboards and illustrations into animated narrative clips.

Generate TikTok, Shorts, and Reels content with ready-to-publish synchronized audio.

Model Version Notes

How to Access and Deploy the viduq3 API on CometAPI

Step 2: Test the viduq3 API for Free in the Playground

Step 3: Deploy the viduq3 API in Production

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.

POST/v1/videos

Sample code and API for Vidu Q3

POST

/v1/videos

# Create a video with viduq3
# Step 1: Submit the video generation request
echo "Submitting video generation request..."
response=$(curl -s https://api.cometapi.com/v1/videos \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F "model=viduq3" \
  -F "prompt=Ultra-realistic cinematic shot of an astronaut walking slowly through soft fog, volumetric light in light blue and pale amber tones, shallow depth of field, 35mm film texture, graceful camera movement." \
  -F "seconds=1" \
  -F "size=960x528")

echo "Response: $response"

# Extract video_id from response (handle JSON with spaces like "id": "xxx")
video_id=$(echo "$response" | tr -d '
' | sed 's/.*"id"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/')
echo "Video ID: $video_id"

# Step 2: Poll for progress until 100%
echo ""
echo "Checking video generation progress..."
while true; do
  status_response=$(curl -s "https://api.cometapi.com/v1/videos/$video_id" \
    -H "Authorization: Bearer $COMETAPI_KEY")

  progress=$(echo "$status_response" | grep -o '"progress"[[:space:]]*:[[:space:]]*"\?[^",}]*"\?' | head -1 | sed 's/.*:[[:space:]]*"\?//;s/"$//')
  status=$(echo "$status_response" | grep -o '"status"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1 | sed 's/.*"status"[[:space:]]*:[[:space:]]*"//;s/"$//')

  echo "Progress: $progress, Status: $status"

  if [ "$status" = "FAILURE" ] || [ "$status" = "failed" ] || [ "$status" = "error" ]; then
    echo "Video generation failed!"
    exit 1
  fi

  if [ "$progress" = "100%" ] || [ "$progress" = "100" ] || [ "$status" = "completed" ] || [ "$status" = "success" ]; then
    echo "Video generation completed!"
    break
  fi

  sleep 10
done

# Step 3: Download the video to output directory
echo ""
echo "Downloading video to ./output/$video_id.mp4..."
mkdir -p ./output
curl -s "https://api.cometapi.com/v1/videos/$video_id/content" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -o "./output/$video_id.mp4"

if [ -f "./output/$video_id.mp4" ]; then
  echo "Video saved to ./output/$video_id.mp4"
  ls -la "./output/$video_id.mp4"
else
  echo "Failed to download video"
  exit 1
fi

cURL Code Example

# Create a video with viduq3
# Step 1: Submit the video generation request
echo "Submitting video generation request..."
response=$(curl -s https://api.cometapi.com/v1/videos \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F "model=viduq3" \
  -F "prompt=Ultra-realistic cinematic shot of an astronaut walking slowly through soft fog, volumetric light in light blue and pale amber tones, shallow depth of field, 35mm film texture, graceful camera movement." \
  -F "seconds=1" \
  -F "size=960x528")

echo "Response: $response"

# Extract video_id from response (handle JSON with spaces like "id": "xxx")
video_id=$(echo "$response" | tr -d '\n' | sed 's/.*"id"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/')
echo "Video ID: $video_id"

# Step 2: Poll for progress until 100%
echo ""
echo "Checking video generation progress..."
while true; do
  status_response=$(curl -s "https://api.cometapi.com/v1/videos/$video_id" \
    -H "Authorization: Bearer $COMETAPI_KEY")
  
  progress=$(echo "$status_response" | grep -o '"progress"[[:space:]]*:[[:space:]]*"\?[^",}]*"\?' | head -1 | sed 's/.*:[[:space:]]*"\?//;s/"$//')
  status=$(echo "$status_response" | grep -o '"status"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1 | sed 's/.*"status"[[:space:]]*:[[:space:]]*"//;s/"$//')
  
  echo "Progress: $progress, Status: $status"
  
  if [ "$status" = "FAILURE" ] || [ "$status" = "failed" ] || [ "$status" = "error" ]; then
    echo "Video generation failed!"
    exit 1
  fi
  
  if [ "$progress" = "100%" ] || [ "$progress" = "100" ] || [ "$status" = "completed" ] || [ "$status" = "success" ]; then
    echo "Video generation completed!"
    break
  fi
  
  sleep 10
done

# Step 3: Download the video to output directory
echo ""
echo "Downloading video to ./output/$video_id.mp4..."
mkdir -p ./output
curl -s "https://api.cometapi.com/v1/videos/$video_id/content" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -o "./output/$video_id.mp4"

if [ -f "./output/$video_id.mp4" ]; then
  echo "Video saved to ./output/$video_id.mp4"
  ls -la "./output/$video_id.mp4"
else
  echo "Failed to download video"
  exit 1
fi

Python Code Example

# Create a video with viduq3 using raw HTTP requests
import os
import time
import requests

api_key = os.environ.get("COMETAPI_KEY")
base_url = "https://api.cometapi.com/v1"
headers = {"Authorization": f"Bearer {api_key}"}

# Step 1: Submit the video generation request
print("Submitting video generation request...")
response = requests.post(
    f"{base_url}/videos",
    headers=headers,
    files={
        "model": (None, "viduq3"),
        "prompt": (None, "Ultra-realistic cinematic shot of an astronaut walking slowly through soft fog, volumetric light in light blue and pale amber tones, shallow depth of field, 35mm film texture, graceful camera movement."),
        "seconds": (None, "1"),
        "size": (None, "960x528"),
    },
)

result = response.json()
print(f"Response: {result}")

video_id = result.get("id") or result.get("task_id")
print(f"Video ID: {video_id}")

# Step 2: Poll for progress until 100%
print("\nChecking video generation progress...")
while True:
    try:
        status_response = requests.get(f"{base_url}/videos/{video_id}", headers=headers)
        status_result = status_response.json()

        data = status_result.get("data") or status_result
        progress = data.get("progress", "0%")
        status = data.get("status", "unknown")

        print(f"Progress: {progress}, Status: {status}")

        if status in ["FAILURE", "failed", "error"]:
            print("Video generation failed!")
            print(status_result)
            exit(1)

        if progress == "100%" or progress == 100 or status in ["completed", "success"]:
            print("Video generation completed!")
            break
    except Exception as e:
        print(f"Temporary error: {e}, retrying...")

    time.sleep(10)

# Step 3: Download the video to output directory
print(f"\nDownloading video to ./output/{video_id}.mp4...")
os.makedirs("./output", exist_ok=True)

video_response = requests.get(f"{base_url}/videos/{video_id}/content", headers=headers)

output_path = f"./output/{video_id}.mp4"
with open(output_path, "wb") as f:
    f.write(video_response.content)

if os.path.exists(output_path):
    file_size = os.path.getsize(output_path)
    print(f"Video saved to {output_path}")
    print(f"File size: {file_size} bytes")
else:
    print("Failed to download video")
    exit(1)

JavaScript Code Example

// Create a video with viduq3 using raw HTTP requests
import fs from "fs";
import path from "path";

const apiKey = process.env.COMETAPI_KEY;
const baseUrl = "https://api.cometapi.com/v1";
const headers = { Authorization: `Bearer ${apiKey}` };

function sleep(ms) {
  return new Promise((resolve) => setTimeout(resolve, ms));
}

// Step 1: Submit the video generation request
console.log("Submitting video generation request...");
const formData = new FormData();
formData.append("model", "viduq3");
formData.append("prompt", "Ultra-realistic cinematic shot of an astronaut walking slowly through soft fog, volumetric light in light blue and pale amber tones, shallow depth of field, 35mm film texture, graceful camera movement.");
formData.append("seconds", "1");
formData.append("size", "960x528");

const submitResponse = await fetch(`${baseUrl}/videos`, {
  method: "POST",
  headers,
  body: formData,
});

const result = await submitResponse.json();
console.log("Response:", JSON.stringify(result, null, 2));

const videoId = result.id || result.task_id;
console.log("Video ID:", videoId);

// Step 2: Poll for progress until 100%
console.log("\nChecking video generation progress...");
while (true) {
  try {
    const statusResponse = await fetch(`${baseUrl}/videos/${videoId}`, { headers });
    const statusResult = await statusResponse.json();
    const data = statusResult.data || statusResult;
    const progress = data.progress || "0%";
    const status = data.status || "unknown";

    console.log(`Progress: ${progress}, Status: ${status}`);

    if (status === "FAILURE" || status === "failed" || status === "error") {
      console.log("Video generation failed!");
      console.log(JSON.stringify(statusResult, null, 2));
      process.exit(1);
    }

    if (progress === "100%" || progress === 100 || status === "completed" || status === "success") {
      console.log("Video generation completed!");
      break;
    }
  } catch (e) {
    console.log(`Temporary error: ${e.message}, retrying...`);
  }

  await sleep(10000);
}

// Step 3: Download the video to output directory
console.log(`\nDownloading video to ./output/${videoId}.mp4...`);
fs.mkdirSync("./output", { recursive: true });

const videoResponse = await fetch(`${baseUrl}/videos/${videoId}/content`, { headers });
const outputPath = path.join("./output", `${videoId}.mp4`);
fs.writeFileSync(outputPath, Buffer.from(await videoResponse.arrayBuffer()));

if (fs.existsSync(outputPath)) {
  const stats = fs.statSync(outputPath);
  console.log(`Video saved to ${outputPath}`);
  console.log(`File size: ${stats.size} bytes`);
} else {
  console.log("Failed to download video");
  process.exit(1);
}

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: Vidu
Context: Model specific
Commercial use: Supported

Use cases

Use Vidu Q3 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.

Uptime

Request success rate over the last 30 days, reflecting the reliability of each model provider. CometAPI monitors all connected providers in real time, 24/7.

Respond

302428msAvg. Response

Uptime

57.1%Avg. Uptime

Versions

Review available model identifiers before pinning a production integration.

viduq3-pro

viduq3-turbo

Updates

Follow meaningful availability, pricing and capability changes for Vidu Q3 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.

Jun 1, 2026

API availability confirmed

Vidu Q3 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.

Jun 1, 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

Vidu Q3 API

Pricing

Vidu Video Generation Pricing

Pricing (Per Second)

Model brief

What is Vidu Q3?

Current catalog snapshot

Overview

Technical Specifications of Vidu Q3

What is Vidu Q3?

Main Features of Vidu Q3

Benchmark Performance of Vidu Q3

Vidu Q3 vs Vidu Q3 Turbo vs Kling 2.1

Known Limitations

Representative Use Cases

AI Short Films

Short Drama Production

Advertising and Brand Storytelling

Comic and Manga Adaptation

Social Media Video Creation

Model Version Notes

How to Access and Deploy the viduq3 API on CometAPI

Step 1: Register or Sign in to CometAPI and Obtain Your viduq3 API Key

Step 2: Test the viduq3 API for Free in the Playground

Step 3: Deploy the viduq3 API in Production

FAQ

What are the main limitations of the Vidu Q3 API?

What resolutions are available in the Vidu Q3 API?

When should I choose Vidu Q3 instead of Vidu Q3 Turbo?

Does the Vidu Q3 API support image-to-video generation?

What is the maximum video length supported by Vidu Q3 API?

Can the Vidu Q3 API generate dialogue, music, and video together?

Is Vidu Q3 suitable for AI short films and narrative advertising?

Can Vidu Q3 create multi-character conversations with synchronized speech?

API

One API, production-ready model access

Sample code and API for Vidu Q3

cURL Code Example

Python Code Example

JavaScript Code Example

Capabilities

Use cases

Other models

Uptime

Uptime

Versions

Updates

One page that gets stronger over time.

API availability confirmed

Pricing and limits synced from the catalog

Permanent model entity created

Compare models and continue your research

Vidu Q3 API

Pricing

Vidu Video Generation Pricing

Pricing (Per Second)

Model brief

What is Vidu Q3?

Current catalog snapshot

Overview

Technical Specifications of Vidu Q3

What is Vidu Q3?

Main Features of Vidu Q3

Benchmark Performance of Vidu Q3

Vidu Q3 vs Vidu Q3 Turbo vs Kling 2.1

Known Limitations

Representative Use Cases

AI Short Films

Short Drama Production

Advertising and Brand Storytelling

Comic and Manga Adaptation

Social Media Video Creation

Model Version Notes

How to Access and Deploy the viduq3 API on CometAPI

Step 1: Register or Sign in to CometAPI and Obtain Your viduq3 API Key

Step 2: Test the viduq3 API for Free in the Playground

Step 3: Deploy the viduq3 API in Production

FAQ

What are the main limitations of the Vidu Q3 API?

What resolutions are available in the Vidu Q3 API?