Sora is OpenAI's multi-modal model that generates videos from text, images, or existing video inputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.2per run·~50 / $10
ExamplesView all
A movie trailer-style scene of a 30-year-old astronaut wearing a red wool knit helmet, set against a backdrop of blue skies and a salt desert. Shot in a cinematic style, simulating 35mm film, with rich, vibrant colors.
Drone camera footage of a colossal woolly mammoth trudging through a snowy meadow, its long woolly fur lightly blows in the wind as it walks, snow-covered trees and dramatic mountains in the distance, late afternoon light with wispy clouds and a soft glow from the sun.
A tracking shot following a sleek, anti-gravity vehicle as it weaves through the towering, chrome skyscrapers of a futuristic metropolis in the year 2250. The city is bustling with flying traffic and holographic advertisements. The shot is captured at golden hour, with the sun reflecting off the metallic surfaces of the buildings.
A futuristic electric sports car driving along a cliffside road at golden hour, metallic body reflecting the orange-pink sunset, ocean waves crashing against the rocks below, cinematic wide-angle shot, deep teal and orange color grading, ultra-sharp details of headlights, wheels, and aerodynamic curves, high contrast and dynamic lighting.
A gondolier in a striped shirt rows slowly along a narrow Venetian canal as golden light spills over the water. A couple leans toward each other in the boat, laughing softly. The stone bridge ahead glows warm, and the camera gently glides alongside, ripples catching the light.
A woman in a knitted scarf sits by the window of a train, watching snow-covered mountains flash by. Her reflection in the glass overlays the rushing scenery. The light is pale and wintry; a coffee cup rests in her hands. The camera stays tight on her thoughtful gaze.
In the crowded alley of a Moroccan souk, a spice vendor arranges bright mounds of saffron, turmeric, and paprika. Sunlight filters through wooden latticework, catching dust motes in the air. The vendor smiles at a passing child, the camera pulling in close to the vibrant colors.
A group of anthropomorphic mushrooms having a disco party in the middle of a dark enchanted forest, with glowing neon lights and exaggerated dance moves, their smooth textures and reflective surfaces emphasizing a comical 3D look.
Related Models
README
OpenAI Sora
OpenAI Sora is OpenAI's groundbreaking text-to-video generation model that creates stunning, cinematic videos from text descriptions. Generate high-quality videos with realistic motion, complex scenes, and cinematic style — from simple prompts to detailed descriptions.
Why It Stands Out
- Cinematic quality: Produces professional-grade videos with realistic motion and visual fidelity.
- Complex scene understanding: Handles detailed prompts with multiple subjects, actions, and environments.
- Prompt Enhancer: Built-in AI-powered prompt optimization for better results.
- Flexible resolutions: Choose from 480p to Full HD 1080p based on your needs.
- Multiple aspect ratios: Support for square, portrait, and landscape formats at each resolution.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the video you want to generate. |
| size | No | Output resolution and aspect ratio (default: 1280×720). |
Supported Sizes
| Size | Resolution | Aspect Ratio | Best For |
|---|---|---|---|
| 480×480 | 480p | 1:1 | Quick previews, social squares |
| 480×854 | 480p | 9:16 | Mobile previews, Stories drafts |
| 854×480 | 480p | 16:9 | Widescreen previews |
| 720×720 | 720p | 1:1 | Instagram, social media squares |
| 720×1280 | 720p | 9:16 | TikTok, Reels, Shorts |
| 1280×720 | 720p | 16:9 | YouTube, standard widescreen |
| 1080×1080 | 1080p | 1:1 | High-quality social squares |
| 1080×1920 | 1080p | 9:16 | Premium vertical content |
| 1920×1080 | 1080p | 16:9 | Full HD widescreen, professional |
How to Use
- Write a prompt describing the scene, action, and style you want. Use the Prompt Enhancer for AI-assisted optimization.
- Select size — choose the resolution and aspect ratio that fits your use case.
- Click Run and wait for your video to generate.
- Preview and download the result.
Best Use Cases
- Film & Storytelling — Generate cinematic scenes for short films and narratives.
- Marketing & Advertising — Produce high-quality promotional videos and ad creatives.
- Social Media Content — Create platform-optimized videos for TikTok, YouTube, Instagram, and more.
- Concept Visualization — Bring creative ideas to life before full production.
- Music Videos — Generate visual content for songs and audio tracks.
Pricing
| Resolution Tier | Sizes | Price per video |
|---|---|---|
| 480p | 480×480, 480×854, 854×480 | $0.20 |
| 720p | 720×720, 720×1280, 1280×720 | $0.45 |
| 1080p | 1080×1080, 1080×1920, 1920×1080 | $1.30 |
Pro Tips for Best Quality
- Be detailed in your prompt — describe subject appearance, action, environment, lighting, mood, and camera style.
- Include cinematic keywords like "35mm film," "slow motion," "tracking shot," or "dramatic lighting."
- Specify the visual style: "movie trailer style," "documentary," "animation," etc.
- Start with 480p or 720p for drafts, then generate final versions at 1080p.
- Choose the right aspect ratio for your target platform before generating.
Notes
- Processing time varies based on resolution and current queue load.
- Higher resolutions produce better quality but take longer to generate.
- Please ensure your prompts comply with OpenAI's content guidelines.
New Model
- Try Sora 2: https://wavespeed.ai/models/openai/sora-2
Sora API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/openai/sora with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Sora below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/openai/sora" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "480*480"
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("openai/sora", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "480*480"
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"openai/sora",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "480*480"
}
)
print(output["outputs"][0]) # → URL of the generated outputSora API — Frequently asked questions
What is the Sora API?
Sora is a OpenAI model for video generation, exposed as a REST API on WaveSpeedAI. Sora is OpenAI's multi-modal model that generates videos from text, images, or existing video inputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Sora API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/openai/openai-sora.
How much does Sora cost per run?
Sora starts at $0.20 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Sora accept?
Key inputs: `prompt`, `size`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/openai/openai-sora.
How long does Sora take to generate?
Average end-to-end generation time on WaveSpeedAI is around 53 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Sora outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (OpenAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.