OpenAI ↗Released December 9, 2024

Sora

Undisclosed parameters

Key Specifications

🏆

Arena Rank

Not disclosed

📐

Context Window

Not disclosed

📥

Input Price

per 1M tokens

Not disclosed

📤

Output Price

per 1M tokens

Not disclosed

🧠

Parameters

Undisclosed

🔒

Open Source

No

Best For

Video generation from text

About Sora

Sora is OpenAI's groundbreaking text-to-video model capable of generating realistic 1080p video clips up to 20 seconds long from text descriptions. It demonstrates an understanding of physics, spatial relationships, and temporal consistency that was previously thought impossible for AI video generation. Sora can create complex scenes with multiple characters, specific camera movements, and accurate environmental details. The model represents a major leap in generative video. While OpenAI's initial preview demonstrated up to one-minute videos, the public release in December 2024 supports clips up to 20 seconds. Its release sparked widespread discussion about the future of content creation, filmmaking, and visual media.

Built byOpenAI↗

Compare Sora

See how Sora stacks up against other leading AI models

Sora vs GPT-o3Compare →Sora vs GPT-4oCompare →Sora vs GPT-o1Compare →Sora vs GPT-4.5Compare →Sora vs GPT-4 TurboCompare →

Other OpenAI Models

GPT-o3
200K#2
GPT-4o
128K#2
GPT-o1
200K#3
GPT-4.5
128K#4
GPT-4 Turbo
128K#5

Other Top Models

Claude Opus 4Anthropic
#1
Claude Sonnet 4Anthropic
#3
DeepSeek R1DeepSeek
#3
Gemini 1.5 ProGoogle DeepMind
#4
Gemini 2.5 ProGoogle DeepMind
#4
Grok 3xAI
#5

Explore More

Model Benchmarks →All Models →OpenAI Company Profile →

Frequently Asked Questions

What is Sora?▾
Sora is OpenAI's groundbreaking text-to-video model capable of generating realistic 1080p video clips up to 20 seconds long from text descriptions. It demonstrates an understanding of physics, spatial relationships, and temporal consistency that was previously thought impossible for AI video generation. Sora can create complex scenes with multiple characters, specific camera movements, and accurate environmental details. The model represents a major leap in generative video. While OpenAI's initial preview demonstrated up to one-minute videos, the public release in December 2024 supports clips up to 20 seconds. Its release sparked widespread discussion about the future of content creation, filmmaking, and visual media.
How much does Sora cost?▾
Pricing for Sora has not been publicly disclosed. Check OpenAI's official website for current rates and availability.
What is Sora's context window?▾
The exact context window for Sora has not been publicly disclosed. Check OpenAI's documentation for the latest specifications.
Is Sora open source?▾
No, Sora is a proprietary model available through OpenAI's API. Proprietary models are typically accessible via API endpoints and offer managed infrastructure, support, and regular updates from the provider.
What is Sora best for?▾
Sora is best suited for: Video generation from text. These use cases leverage the model's specific strengths in terms of capability, speed, and cost-effectiveness within OpenAI's model lineup.