- Pricing
- Not published
- Released
- 2y ago
Cost
The original Sora text-to-video model, previewed by OpenAI in February 2024 to red teamers and invited creators. It was never generally released.
How it compares
Level
FlagshipThe lab's most capable generally available line, priced for hard tasks.
Flagship models from other labs
Vs. your stack
Add the models you use to see how this one compares.
Sign inText provenance
EU · product-scopedOpenAI textGrain watermarking
In the EU, ChatGPT-generated text uses textGrain. OpenAI says API customers can opt in globally for select models, so watermarking depends on the product surface and configuration.
Official explanationFrequently asked questions
Quality and benchmarks
The closest alternatives to Sora 1 are Ray1 by Luma AI, Stable Video 3D by Stability AI, and Stable Video Diffusion by Stability AI. They were matched on model kind and release date, with no comparable price.
Ray1Sora 1 vs Ray1Stable Video 3DSora 1 vs Stable Video 3DStable Video DiffusionSora 1 vs Stable Video Diffusion
MiniMax H3 is the best open-weight alternative, rank 11 and the highest-ranked open-weight model on Arena Text to Video. Sora 1 itself is closed.
Licensing and access
No, Sora 1 is not open source or open weights. It is closed with a proprietary license.
Basics
Sora 1 was made by OpenAI and released on February 15, 2024.
Media
Yes, image-to-video (image input) is supported. Video editing (video input) is also supported.
Generated from Vertical Tabs data, updated November 6, 2026.
Discussion
No comments yet
Be the first to share your thoughts.