How does Sora 2 Pro differ from standard Sora 2?

Sora 2 Pro is tuned for higher visual fidelity, handles tougher shots (complex motion, occlusion, physical interactions), and maintains longer per-scene consistency—at the cost of longer render times.

How long does Sora 2 Pro take to render a video?

Benchmark tests show Sora 2 Pro averages approximately 2.1 minutes for a 20-second 1080p clip. Pro prioritizes quality over speed, so expect longer render times than standard Sora 2.

What physics improvements does Sora 2 Pro offer?

Sora 2 Pro improves object permanence and motion fidelity—momentum, buoyancy, and physical interactions appear more realistic with fewer 'teleporting' artifacts common in earlier video models.

When should I choose Sora 2 Pro over Google Veo 3?

Choose Sora 2 Pro for OpenAI ecosystem integration, likeness injection, and complex physical scenes. Veo 3 may offer faster generation and different pricing—evaluate based on your latency and budget needs.

Does Sora 2 Pro support likeness injection (cameos)?

Yes, Sora 2 Pro can insert a user's captured likeness into generated scenes. OpenAI has built-in consent workflows and revocation mechanisms to address privacy and misuse risks.

What resolution and duration does Sora 2 Pro support?

Sora 2 Pro supports up to 1080p resolution. It's optimized for high-quality short clips, typically in the single-digit to low-tens of seconds range for maximum fidelity.

Does Sora 2 Pro generate synchronized audio with video?

Yes, Sora 2 Pro generates video frames together with synchronized audio including dialogue, ambient sound, and sound effects—not produced separately but as a unified output.

Can Sora 2 Pro use reference images to guide video generation?

Yes, Sora 2 Pro supports input_reference workflows where JPEG/PNG/WEBP images act as composition anchors to guide the generated video's starting frame or style.

OpenAI

Available

sora-2-pro

Sora 2 Pro API

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.

Starting price

$0.24 / second

Usage-based billing

API health

Available

Production endpoint

Response

Async ready

Observed API response

Released

Jun 1, 2026

OpenAI

Playground

Try Sora 2 Pro 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

$1.20

Estimated CometAPI usage cost

10-second test

$2.40

Estimated CometAPI usage cost

15-second test

$3.60

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.

Model Name	Tags	Orientation	Resolution	Price
sora-2-pro	videos	Portrait	720x1280	$0.24 / sec
sora-2-pro	videos	Landscape	1280x720	$0.24 / sec
sora-2-pro	videos	Portrait (High Res)	1024x1792	$0.40 / sec
sora-2-pro	videos	Landscape (High Res)	1792x1024	$0.40 / sec
sora-2-pro-all	-	Universal / All	-	$0.80000

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 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.

Canonical model identity stays stable as pricing and limits change.

Live model data

Current catalog snapshot

Availability

Available

Starting price

$0.24 / second

Context

See capabilities

Catalog date

Jun 1, 2026

Overview

A practical overview of Sora 2 Pro, including important behavior and integration considerations.

Key features

Multimodal generation (video + audio) — Sora-2-Pro generates video frames together with synchronized audio (dialogue, ambient sound, SFX) rather than producing video and audio separately.
Higher fidelity / “Pro” tier — tuned for higher visual fidelity, tougher shots (complex motion, occlusion, and physical interactions), and longer per-scene consistency than Sora-2 (non-Pro). It may take longer to render than the standard Sora-2 model.
Input versatility — supports pure text prompts, and can accept image input frames or reference images to guide composition (input_reference workflows).
Cameos / likeness injection — can insert a user’s captured likeness into generated scenes with consent workflows in the app.
Physical plausibility: improved object permanence and motion fidelity (e.g., momentum, buoyancy), reducing unrealistic “teleporting” artifacts common in earlier systems.
Controllability: supports structured prompts and shot-level directions so creators can specify camera, lighting, and multi-shot sequences.

Technical details & integration surface

Model family: Sora 2 (base) and Sora 2 Pro (high-quality variant).
Input modalities: text prompts, image reference, and short recorded cameo-video/audio for likeness.
Output modalities: encoded video (with audio) — parameters exposed through /v1/videos endpoints (model selection via model: "sora-2-pro"). API surface follows OpenAI’s videos endpoint family for create/retrieve/list/delete operations.

Training & architecture (public summary): OpenAI describes Sora 2 as trained on large-scale video data with post-training to improve world simulation; specifics (model size, exact datasets, and tokenization) are not publicly enumerated in line-by-line detail. Expect heavy compute, specialized video tokenizers/architectures and multi-modal alignment components.

API endpoints & workflow: show a job-based workflow: submit a POST creation request (model="sora-2-pro"), receive a job id or location, then poll or wait for completion and download the resulting file(s). Common parameters in published examples include prompt, seconds/duration, size/resolution, and input_reference for image-guided starts.

Typical parameters :

model: "sora-2-pro"
prompt: natural language scene description, optionally with dialogue cues
seconds / duration: target clip length ( Pro supports the highest quality in available durations)
size / resolution: community reports indicate Pro supports up to 1080p in many use cases.

Content inputs: image files (JPEG/PNG/WEBP) can be supplied as a frame or reference; when used, the image should match the target resolution and act as a composition anchor.

Rendering behavior: Pro is tuned to prioritize frame-to-frame coherence and realistic physics; this typically implies longer compute time and higher cost per clip than non-Pro variants.

Benchmark performance

Qualitative strengths: OpenAI improved realism, physics consistency, and synchronized audio** versus prior video models. Other VBench results indicate Sora-2 and derivatives sit at or near the top of contemporary closed-source and temporal coherence.

Independent timing/throughput (example bench): Sora-2-Pro averaged ~2.1 minutes for 20-second 1080p clips in one comparison, while a competitor (Runway Gen-3 Alpha Turbo) was faster (~1.7 minutes) on the same task — tradeoffs are quality vs render latency and platform optimization.

Limitations (practical & safety)

Not perfect physics/consistency — improved but not flawless; artifacts, unnatural motion, or audio sync errors can still occur.
Duration & compute constraints — long clips are compute-intensive; many practical workflows limit clips to short durations (e.g., single-digit to low-tens of seconds for high-quality outputs).
Privacy / consent risks — likeness injection (“cameos”) raises consent and mis-/disinformation risks; OpenAI has explicit safety controls and revocation mechanisms in the app, but responsible integration is required.
Cost & latency — Pro-quality renders can be more expensive and slower than lighter models or competitors; factor in per-second/per-render billing and queuing.
Safety content filtering — generation of harmful or copyrighted content is restricted; the model and platform include safety layers and moderation.

Typical and recommended use cases

Use cases:

Marketing & ads prototypes — rapidly create cinematic proofs of concept.
Previsualization — storyboards, camera blocking, shot visualization.
Short social content — stylized clips with synchronized dialogue and SFX.
How to access Sora 2 Pro API

Log in to cometapi.com. If you are not our user yet, please register first. Sign into your CometAPI console. Get the access credential API key of the interface. Click “Add Token” at the API token in the personal center, get the token key: sk-xxxxx and submit.

cometapi-key

Step 2: Send Requests to Sora 2 Pro API

Select the “sora-2-pro” endpoint to send the API request and set the request body. The request method and request body are obtained from our website API doc. Our website also provides Apifox test for your convenience. Replace <YOUR_API_KEY> with your actual CometAPI key from your account. base url is office Create video

Insert your question or request into the content field—this is what the model will respond to . Process the API response to get the generated answer.

Step 3: Retrieve and Verify Results

Process the API response to get the generated answer. After processing, the API responds with the task status and output data.

Internal training / simulation — generate scenario visuals for RL or robotics research (with care).
Creative production — when combined with human editing (stitching short clips, grade, replace audio).

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 Sora 2 Pro

Sora-2-pro is OpenAI’s flagship video+audio generation model designed to create short, highly realistic video clips with synchronized dialogue, sound effects, and stronger physical/world simulation than previous video models. It’s positioned as the higher-quality “Pro” variant available to paying users and via the API for programmatic generation. The model emphasizes controllability, temporal coherence, and audio synchronization for cinematic and social use cases.

POST

/v1/videos

# Create a video with sora-2-pro
# 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=sora-2-pro" \
  -F "prompt=A calico cat playing a piano on stage")

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")

  # Parse progress from "progress": "0%" format
  progress=$(echo "$status_response" | grep -o '"progress":"[^"]*"' | head -1 | sed 's/"progress":"//;s/"$//')
  # Parse status from the outer level
  status=$(echo "$status_response" | grep -o '"status":"[^"]*"' | head -1 | sed 's/"status":"//;s/"$//')

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

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

  if [ "$status" = "FAILURE" ] || [ "$status" = "failed" ]; then
    echo "Video generation failed!"
    echo "$status_response"
    exit 1
  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 sora-2-pro
# 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=sora-2-pro" \
  -F "prompt=A calico cat playing a piano on stage")

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")
  
  # Parse progress from "progress": "0%" format
  progress=$(echo "$status_response" | grep -o '"progress":"[^"]*"' | head -1 | sed 's/"progress":"//;s/"$//')
  # Parse status from the outer level
  status=$(echo "$status_response" | grep -o '"status":"[^"]*"' | head -1 | sed 's/"status":"//;s/"$//')
  
  echo "Progress: $progress, Status: $status"
  
  if [ "$progress" = "100%" ]; then
    echo "Video generation completed!"
    break
  fi
  
  if [ "$status" = "FAILURE" ] || [ "$status" = "failed" ]; then
    echo "Video generation failed!"
    echo "$status_response"
    exit 1
  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 sora-2-pro 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, "sora-2-pro"),
        "prompt": (None, "A calico cat playing a piano on stage"),
    },
)

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

video_id = result.get("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()

        # Parse progress and status from response
        data = status_result.get("data", {})
        if data is None:
            data = {}
        progress = data.get("progress", "0%")
        status = data.get("status", "unknown")

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

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

        if progress == "100%":
            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 sora-2-pro 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";

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

async function main() {
  // Step 1: Submit the video generation request
  console.log("Submitting video generation request...");

  const formData = new FormData();
  formData.append("model", "sora-2-pro");
  formData.append("prompt", "A calico cat playing a piano on stage");

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

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

  const videoId = result.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: {
          Authorization: `Bearer ${apiKey}`,
        },
      });

      const text = await statusResponse.text();
      if (text.startsWith("<")) {
        console.log("Temporary server error, retrying...");
        await sleep(10000);
        continue;
      }

      const statusResult = JSON.parse(text);

      // Parse progress and status from response
      const data = statusResult.data || {};
      const progress = data.progress || "0%";
      const status = data.status || "unknown";

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

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

      if (progress === "100%") {
        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...`);

  const outputDir = "./output";
  if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
  }

  const videoResponse = await fetch(`${baseUrl}/videos/${videoId}/content`, {
    headers: {
      Authorization: `Bearer ${apiKey}`,
    },
  });

  const outputPath = path.join(outputDir, `${videoId}.mp4`);
  const videoBuffer = Buffer.from(await videoResponse.arrayBuffer());
  fs.writeFileSync(outputPath, videoBuffer);

  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);
  }
}

main().catch(console.error);

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: OpenAI
Context: Model specific
Commercial use: Supported

Use cases

Use Sora 2 Pro 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.

Updates

Follow meaningful availability, pricing and capability changes for Sora 2 Pro 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

Sora 2 Pro 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.

Oct 7, 2025

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

OpenAI

Available

sora-2-pro

Sora 2 Pro API

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.

Starting price

$0.24 / second

Usage-based billing

API health

Available

Production endpoint

Response

Async ready

Observed API response

Released

Jun 1, 2026

OpenAI

Playground

Try Sora 2 Pro 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

$1.20

Estimated CometAPI usage cost

10-second test

$2.40

Estimated CometAPI usage cost

15-second test

$3.60

Estimated CometAPI usage cost

Model Name	Tags	Orientation	Resolution	Price
sora-2-pro	videos	Portrait	720x1280	$0.24 / sec
sora-2-pro	videos	Landscape	1280x720	$0.24 / sec
sora-2-pro	videos	Portrait (High Res)	1024x1792	$0.40 / sec
sora-2-pro	videos	Landscape (High Res)	1792x1024	$0.40 / sec
sora-2-pro-all	-	Universal / All	-	$0.80000

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 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.

Canonical model identity stays stable as pricing and limits change.

Live model data

Current catalog snapshot

Availability

Available

Starting price

$0.24 / second

Context

See capabilities

Catalog date

Jun 1, 2026

Overview

A practical overview of Sora 2 Pro, including important behavior and integration considerations.

Key features

Multimodal generation (video + audio) — Sora-2-Pro generates video frames together with synchronized audio (dialogue, ambient sound, SFX) rather than producing video and audio separately.
Higher fidelity / “Pro” tier — tuned for higher visual fidelity, tougher shots (complex motion, occlusion, and physical interactions), and longer per-scene consistency than Sora-2 (non-Pro). It may take longer to render than the standard Sora-2 model.
Input versatility — supports pure text prompts, and can accept image input frames or reference images to guide composition (input_reference workflows).
Cameos / likeness injection — can insert a user’s captured likeness into generated scenes with consent workflows in the app.
Physical plausibility: improved object permanence and motion fidelity (e.g., momentum, buoyancy), reducing unrealistic “teleporting” artifacts common in earlier systems.
Controllability: supports structured prompts and shot-level directions so creators can specify camera, lighting, and multi-shot sequences.

Technical details & integration surface

Typical parameters :

model: "sora-2-pro"
prompt: natural language scene description, optionally with dialogue cues
seconds / duration: target clip length ( Pro supports the highest quality in available durations)
size / resolution: community reports indicate Pro supports up to 1080p in many use cases.

Content inputs: image files (JPEG/PNG/WEBP) can be supplied as a frame or reference; when used, the image should match the target resolution and act as a composition anchor.

Rendering behavior: Pro is tuned to prioritize frame-to-frame coherence and realistic physics; this typically implies longer compute time and higher cost per clip than non-Pro variants.

Benchmark performance

Limitations (practical & safety)

Not perfect physics/consistency — improved but not flawless; artifacts, unnatural motion, or audio sync errors can still occur.
Duration & compute constraints — long clips are compute-intensive; many practical workflows limit clips to short durations (e.g., single-digit to low-tens of seconds for high-quality outputs).
Privacy / consent risks — likeness injection (“cameos”) raises consent and mis-/disinformation risks; OpenAI has explicit safety controls and revocation mechanisms in the app, but responsible integration is required.
Cost & latency — Pro-quality renders can be more expensive and slower than lighter models or competitors; factor in per-second/per-render billing and queuing.
Safety content filtering — generation of harmful or copyrighted content is restricted; the model and platform include safety layers and moderation.

Typical and recommended use cases

Use cases:

Marketing & ads prototypes — rapidly create cinematic proofs of concept.
Previsualization — storyboards, camera blocking, shot visualization.
Short social content — stylized clips with synchronized dialogue and SFX.
How to access Sora 2 Pro API

cometapi-key

Step 2: Send Requests to Sora 2 Pro API

Insert your question or request into the content field—this is what the model will respond to . Process the API response to get the generated answer.

Step 3: Retrieve and Verify Results

Process the API response to get the generated answer. After processing, the API responds with the task status and output data.

Internal training / simulation — generate scenario visuals for RL or robotics research (with care).
Creative production — when combined with human editing (stitching short clips, grade, replace audio).

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 Sora 2 Pro

POST

/v1/videos

# Create a video with sora-2-pro
# 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=sora-2-pro" \
  -F "prompt=A calico cat playing a piano on stage")

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")

  # Parse progress from "progress": "0%" format
  progress=$(echo "$status_response" | grep -o '"progress":"[^"]*"' | head -1 | sed 's/"progress":"//;s/"$//')
  # Parse status from the outer level
  status=$(echo "$status_response" | grep -o '"status":"[^"]*"' | head -1 | sed 's/"status":"//;s/"$//')

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

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

  if [ "$status" = "FAILURE" ] || [ "$status" = "failed" ]; then
    echo "Video generation failed!"
    echo "$status_response"
    exit 1
  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 sora-2-pro
# 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=sora-2-pro" \
  -F "prompt=A calico cat playing a piano on stage")

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")
  
  # Parse progress from "progress": "0%" format
  progress=$(echo "$status_response" | grep -o '"progress":"[^"]*"' | head -1 | sed 's/"progress":"//;s/"$//')
  # Parse status from the outer level
  status=$(echo "$status_response" | grep -o '"status":"[^"]*"' | head -1 | sed 's/"status":"//;s/"$//')
  
  echo "Progress: $progress, Status: $status"
  
  if [ "$progress" = "100%" ]; then
    echo "Video generation completed!"
    break
  fi
  
  if [ "$status" = "FAILURE" ] || [ "$status" = "failed" ]; then
    echo "Video generation failed!"
    echo "$status_response"
    exit 1
  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 sora-2-pro 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, "sora-2-pro"),
        "prompt": (None, "A calico cat playing a piano on stage"),
    },
)

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

video_id = result.get("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()

        # Parse progress and status from response
        data = status_result.get("data", {})
        if data is None:
            data = {}
        progress = data.get("progress", "0%")
        status = data.get("status", "unknown")

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

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

        if progress == "100%":
            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 sora-2-pro 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";

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

async function main() {
  // Step 1: Submit the video generation request
  console.log("Submitting video generation request...");

  const formData = new FormData();
  formData.append("model", "sora-2-pro");
  formData.append("prompt", "A calico cat playing a piano on stage");

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

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

  const videoId = result.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: {
          Authorization: `Bearer ${apiKey}`,
        },
      });

      const text = await statusResponse.text();
      if (text.startsWith("<")) {
        console.log("Temporary server error, retrying...");
        await sleep(10000);
        continue;
      }

      const statusResult = JSON.parse(text);

      // Parse progress and status from response
      const data = statusResult.data || {};
      const progress = data.progress || "0%";
      const status = data.status || "unknown";

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

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

      if (progress === "100%") {
        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...`);

  const outputDir = "./output";
  if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
  }

  const videoResponse = await fetch(`${baseUrl}/videos/${videoId}/content`, {
    headers: {
      Authorization: `Bearer ${apiKey}`,
    },
  });

  const outputPath = path.join(outputDir, `${videoId}.mp4`);
  const videoBuffer = Buffer.from(await videoResponse.arrayBuffer());
  fs.writeFileSync(outputPath, videoBuffer);

  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);
  }
}

main().catch(console.error);

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: OpenAI
Context: Model specific
Commercial use: Supported

Use cases

Use Sora 2 Pro 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.

Updates

Follow meaningful availability, pricing and capability changes for Sora 2 Pro 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

Sora 2 Pro 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.

Oct 7, 2025

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

Sora 2 Pro API

Playground

Pricing

Model brief

What is Sora 2 Pro?

Current catalog snapshot

Overview

Key features

Technical details & integration surface

Benchmark performance

Limitations (practical & safety)

Typical and recommended use cases

Step 1: Sign Up for API Key

Step 2: Send Requests to Sora 2 Pro API

Step 3: Retrieve and Verify Results

FAQ

How does Sora 2 Pro differ from standard Sora 2?

How long does Sora 2 Pro take to render a video?

What physics improvements does Sora 2 Pro offer?

When should I choose Sora 2 Pro over Google Veo 3?

Does Sora 2 Pro support likeness injection (cameos)?

What resolution and duration does Sora 2 Pro support?

Does Sora 2 Pro generate synchronized audio with video?

Can Sora 2 Pro use reference images to guide video generation?

API

One API, production-ready model access

Sample code and API for Sora 2 Pro

cURL Code Example

Python Code Example

JavaScript Code Example

Capabilities

Use cases

Other models

Uptime

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

Sora 2 Pro API

Playground

Pricing

Model brief

What is Sora 2 Pro?

Current catalog snapshot

Overview

Key features

Technical details & integration surface

Benchmark performance

Limitations (practical & safety)

Typical and recommended use cases

Step 1: Sign Up for API Key

Step 2: Send Requests to Sora 2 Pro API

Step 3: Retrieve and Verify Results

FAQ

How does Sora 2 Pro differ from standard Sora 2?

How long does Sora 2 Pro take to render a video?

What physics improvements does Sora 2 Pro offer?

When should I choose Sora 2 Pro over Google Veo 3?

Does Sora 2 Pro support likeness injection (cameos)?

What resolution and duration does Sora 2 Pro support?

Does Sora 2 Pro generate synchronized audio with video?

Can Sora 2 Pro use reference images to guide video generation?

API

One API, production-ready model access

Sample code and API for Sora 2 Pro

cURL Code Example

Python Code Example

JavaScript Code Example

Capabilities

Use cases

Other models

Uptime

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