OpenAI

Sora 2

Name: Sora 2
Brand: OpenAI
Price: 0.1 USD
Availability: InStock

AI Video Generation Model

Video

OpenAI's video generation model supporting text-to-video and image-to-video at 720p resolution with durations up to 20 seconds

Try Model

20 seconds

Max Video Duration

Supported Modes

Text to Video Image to Video

Active

Details

Model ID

sora-2

Creator

OpenAI

Family

sora

Ready to integrate?

Access sora-2 via our unified API.

Create Account

Available at 3 providers

Starting from

$0.100 /second via fal.ai, OpenAI, Replicate

Prices shown are in USD

See all providers

Provider Performance

Fastest generation through openai at 1,444ms median latency with 100.0% success rate.

Aggregated from real API requests over the last 30 days.

Generation Time

openai

p95: 59,437ms

Success Rate

openai

100.0%

10 / 10 requests

Provider Rankings

#	Provider	p50 Gen Time	p95 Gen Time	Success Rate	TTFB (p50)
1	openai	1,444ms	59,437ms	100.0%	—

Data updated every 15 minutes. Based on all API requests through Lumenfall over the last 30 days.

Providers & Pricing (4)

Sora 2 is available from 4 providers, with per-video pricing starting at $0.1 through fal.ai.

fal.ai

Text to Video

fal/sora-2

Provider Model ID: fal-ai/sora-2/text-to-video

$0.100 /second

View pricing details

fal.ai

Image to Video

fal/sora-2-i2v

Provider Model ID: fal-ai/sora-2/image-to-video

$0.100 /second

View pricing details

OpenAI

Text to Video Image to Video

openai/sora-2

Provider Model ID: sora-2

$0.100 /second

View pricing details

Replicate

Text to Video Image to Video

replicate/sora-2

Provider Model ID: openai/sora-2

$0.100 /second

View pricing details

Sora 2 API Async video generation

Integrate Sora 2 via Lumenfall’s OpenAI-compatible API to generate high-fidelity videos up to 20 seconds long with 720p resolution.

Base URL

https://api.lumenfall.ai/v1

Model

sora-2

Code Examples

Text to Video

/v1/videos/generations

# Step 1: Submit video generation request

VIDEO_ID=$(curl -s -X POST \

  https://api.lumenfall.ai/v1/videos \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "sora-2",

    "prompt": "",

    "size": "1024x1024"

  }' | jq -r '.id')

echo "Video ID: $VIDEO_ID"

# Step 2: Poll for completion

while true; do

  RESULT=$(curl -s \

    https://api.lumenfall.ai/v1/videos/$VIDEO_ID \

    -H "Authorization: Bearer $LUMENFALL_API_KEY")

  STATUS=$(echo $RESULT | jq -r '.status')

  echo "Status: $STATUS"

  if [ "$STATUS" = "completed" ]; then

    echo $RESULT | jq -r '.output.url'

    break

  elif [ "$STATUS" = "failed" ]; then

    echo $RESULT | jq -r '.error.message'

    break

fi

  sleep 5

done

const BASE_URL = 'https://api.lumenfall.ai/v1';

const API_KEY = 'YOUR_API_KEY';

// Step 1: Submit video generation request

const submitRes = await fetch(`${BASE_URL}/videos`, {

  method: 'POST',

  headers: {

    'Authorization': `Bearer ${API_KEY}`,

    'Content-Type': 'application/json'

},

  body: JSON.stringify({

    model: 'sora-2',

    prompt: '',

    size: '1024x1024'

})

});

const { id: videoId } = await submitRes.json();

console.log('Video ID:', videoId);

// Step 2: Poll for completion

while (true) {

  const pollRes = await fetch(`${BASE_URL}/videos/${videoId}`, {

    headers: { 'Authorization': `Bearer ${API_KEY}` }

});

  const result = await pollRes.json();

  if (result.status === 'completed') {

    console.log('Video URL:', result.output.url);

    break;

  } else if (result.status === 'failed') {

    console.error('Error:', result.error.message);

    break;

  await new Promise(r => setTimeout(r, 5000));

import requests

import time

BASE_URL = "https://api.lumenfall.ai/v1"

API_KEY = "YOUR_API_KEY"

HEADERS = {

    "Authorization": f"Bearer {API_KEY}",

    "Content-Type": "application/json"

# Step 1: Submit video generation request

response = requests.post(

    f"{BASE_URL}/videos",

    headers=HEADERS,

    json={

        "model": "sora-2",

        "prompt": "",

        "size": "1024x1024"

video_id = response.json()["id"]

print(f"Video ID: {video_id}")

# Step 2: Poll for completion

while True:

    result = requests.get(

        f"{BASE_URL}/videos/{video_id}",

        headers=HEADERS

    ).json()

    if result["status"] == "completed":

        print(f"Video URL: {result['output']['url']}")

        break

    elif result["status"] == "failed":

        print(f"Error: {result['error']['message']}")

        break

    time.sleep(5)

Image to Video

/v1/videos/generations

# Step 1: Submit image-to-video request

VIDEO_ID=$(curl -s -X POST \

  https://api.lumenfall.ai/v1/videos \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "sora-2",

    "prompt": "",

    "image_url": "https://example.com/start-frame.jpg",

    "duration": "10",

    "aspect_ratio": "16:9"

  }' | jq -r '.id')

echo "Video ID: $VIDEO_ID"

# Step 2: Poll for completion

while true; do

  RESULT=$(curl -s \

    https://api.lumenfall.ai/v1/videos/$VIDEO_ID \

    -H "Authorization: Bearer $LUMENFALL_API_KEY")

  STATUS=$(echo $RESULT | jq -r '.status')

  echo "Status: $STATUS"

  if [ "$STATUS" = "completed" ]; then

    echo $RESULT | jq -r '.output.url'

    break

  elif [ "$STATUS" = "failed" ]; then

    echo $RESULT | jq -r '.error.message'

    break

fi

  sleep 5

done

const BASE_URL = 'https://api.lumenfall.ai/v1';

const API_KEY = 'YOUR_API_KEY';

// Step 1: Submit image-to-video request

const submitRes = await fetch(`${BASE_URL}/videos`, {

  method: 'POST',

  headers: {

    'Authorization': `Bearer ${API_KEY}`,

    'Content-Type': 'application/json'

},

  body: JSON.stringify({

    model: 'sora-2',

    prompt: '',

    image_url: 'https://example.com/start-frame.jpg',

    duration: '10',

    aspect_ratio: '16:9'

})

});

const { id: videoId } = await submitRes.json();

console.log('Video ID:', videoId);

// Step 2: Poll for completion

while (true) {

  const pollRes = await fetch(`${BASE_URL}/videos/${videoId}`, {

    headers: { 'Authorization': `Bearer ${API_KEY}` }

});

  const result = await pollRes.json();

  if (result.status === 'completed') {

    console.log('Video URL:', result.output.url);

    break;

  } else if (result.status === 'failed') {

    console.error('Error:', result.error.message);

    break;

  await new Promise(r => setTimeout(r, 5000));

import requests

import time

BASE_URL = "https://api.lumenfall.ai/v1"

API_KEY = "YOUR_API_KEY"

HEADERS = {

    "Authorization": f"Bearer {API_KEY}",

    "Content-Type": "application/json"

# Step 1: Submit image-to-video request

response = requests.post(

    f"{BASE_URL}/videos",

    headers=HEADERS,

    json={

        "model": "sora-2",

        "prompt": "",

        "image_url": "https://example.com/start-frame.jpg",

        "duration": "10",

        "aspect_ratio": "16:9"

video_id = response.json()["id"]

print(f"Video ID: {video_id}")

# Step 2: Poll for completion

while True:

    result = requests.get(

        f"{BASE_URL}/videos/{video_id}",

        headers=HEADERS

    ).json()

    if result["status"] == "completed":

        print(f"Video URL: {result['output']['url']}")

        break

    elif result["status"] == "failed":

        print(f"Error: {result['error']['message']}")

        break

    time.sleep(5)

Parameter Reference

Required Supported Not available

Core Parameters

Parameter	Type	Description	Modes
`prompt`	string	Required. Text prompt for video generation	T2V I2V
`duration`	number	Video duration in seconds	T2V I2V

Size & Layout

Parameter	Type	Description	Modes
`size`	string	Video dimensions as WxH pixels (e.g. "1920x1080") or aspect ratio (e.g. "16:9") `auto` `1365x768` `768x1365` WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.	T2V I2V
`aspect_ratio`	string	Aspect ratio of the output video (e.g. "16:9", "1:1") `auto` `9:16` `16:9` Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.	T2V I2V
`resolution`	string	Output resolution tier (e.g. "1K", "4K") `auto` `1K` Controls scale independently of shape. Higher tiers produce larger videos and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.	T2V I2V

Output	`size`		`aspect_ratio` + `resolution`
Flexible
Auto	`"auto"`	—	Model chooses optimal dimensions

1K 2 sizes

Output	`size`		`aspect_ratio` + `resolution`
768 × 1365	`"768x1365"`	or	`"9:16"` + `"1K"`
1365 × 768	`"1365x768"`	or	`"16:9"` + `"1K"`

How these parameters work

size

Exact pixel dimensions

"1920x1080"

aspect_ratio

Shape only, default scale

"16:9"

resolution

Scale tier, preserves shape

"1K"

Priority when combined

size › aspect_ratio + resolution › aspect_ratio › resolution

size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.

How matching works

Shape matching – we pick the closest supported ratio. Ask for 7:1 on a model with 4:1 and 8:1, you get 8:1.

Scale matching – providers use different tier formats: K tiers (0.5K 1K 2K 4K) or megapixel tiers (0.25 1). If the exact tier isn't available, you get the nearest one.

Dimension clamping – if a model has pixel limits, we clamp dimensions to fit and keep the aspect ratio intact.

Output & Format

Parameter	Type	Description	Modes
`n`	integer	Number of videos to generate Default: `1` Gateway generates multiple videos in parallel even if provider only supports 1.	T2V I2V

Additional Parameters

Parameter	Type	Description	Modes
`character_ids` fal	array	Up to two character IDs (from create-character) to use in the video. Refer to characters by name in the prompt. When set, only the OpenAI provider is used.	T2V I2V
`delete_video` fal	boolean	Whether to delete the video after generation for privacy reasons. If True, the video cannot be used for remixing and will be permanently deleted.	T2V I2V
`detect_and_block_ip` fal	boolean	If enabled, the prompt (and image for image-to-video) will be checked for known intellectual property references and the request will be blocked if any are detected.	T2V I2V
`input_reference` replicate	string	An optional image to use as the first frame of the video. The image must be the same aspect ratio as the video.	T2V I2V
`model` fal	string	The model to use for the generation. When the default model is selected, the latest snapshot of the model will be used - otherwise, select a specific snapshot of the model. `sora-2` `sora-2-2025-10-06` `sora-2-2025-12-08`	T2V I2V
`openai_api_key` replicate	string	Optional: Your OpenAI API key. If you use your own OpenAI API key, you will be charged directly by OpenAI.	T2V I2V
`seconds` replicate	integer	Duration of the video in seconds	T2V I2V

Parameter Normalization

How we handle parameters across different providers

Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:

Behavior	What happens	Example
`passthrough`	Sent as-is to the provider	style, quality
`renamed`	Same value, mapped to the field name the provider expects	prompt
`converted`	Transformed to the provider's native format	size
`emulated`	Works even if the provider has no concept of it	n, response_format

Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.

Full API Reference Authentication, endpoints, and more

Sora 2 FAQ

How much does Sora 2 cost?

Sora 2 starts at $0.1 per video through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

How do I use Sora 2 via API?

You can use Sora 2 through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "sora-2". Code examples are available in Python, JavaScript, and cURL.

Which providers offer Sora 2?

Sora 2 is available through fal.ai, OpenAI, and Replicate on Lumenfall. Lumenfall automatically routes requests to the best available provider.

Overview

Sora 2 is a high-fidelity video generation model developed by OpenAI that transforms text prompts or static images into cinematic video sequences. It represents an evolution in the Sora family, capable of producing content at 720p resolution with extended durations reaching up to 20 seconds. This model is distinguished by its ability to maintain temporal consistency and complex motion dynamics over longer spans than many first-generation video models.

Strengths

Temporal Consistency: Maintains the identity of characters, objects, and environmental details across the entire 20-second duration, minimizing the “morphing” or warping effects common in shorter-clip models.
Physical Simulation: Demonstrates a sophisticated understanding of physical interactions, such as fluid dynamics, lighting reflections, and gravity, leading to more realistic movement.
Multimodal Input Flexibility: Supports both text-to-video for purely generative tasks and image-to-video for animating existing assets or extending still photography into motion.
Enhanced Resolution: Outputs native 720p video, providing sufficient clarity for social media content, prototyping, and digital backgrounds without immediate need for upscaling.

Limitations

Causal Reasoning: While physically grounded, the model may still struggle with complex “cause and effect” sequences, such as a character taking a bite out of a cookie and the cookie not showing a bite mark.
Spatial Confusion: In high-action scenes involving multiple moving parts (e.g., a crowded street), the model can occasionally mix up left/right orientations or produce impossible limb movements.
Resolution Ceiling: At 720p, it lacks the native 4K or 1080p detail required for professional film production pipelines without significant post-processing.

Technical Background

Sora 2 utilizes a diffusion transformer (DiT) architecture, which combines the scaling properties of transformers with the generative capabilities of diffusion models. It operates on spacetime patches, treating video data as a three-dimensional collection of patches that allow the model to train on diverse aspect ratios and resolutions. This architecture enables the model to look ahead and behind in a sequence to ensure global coherence rather than generating frames in a strictly linear, autoregressive fashion.

Best For

Sora 2 is best suited for rapid prototyping in creative agencies, generating b-roll for digital marketing, and creating environmental backgrounds for web design. It excels at animating conceptual art where maintaining character consistency is a priority. This model is available for testing and integration through Lumenfall’s unified API and playground, allowing developers to compare its outputs directly against other video generation frameworks.

Try Sora 2 in Playground

Generate images with custom prompts — no API key needed.

Open Playground