OpenAI
Sora 1
InputText, Image, VideoOutputVideo
The original Sora text-to-video model, previewed by OpenAI in February 2024 to red teamers and invited creators. It was never generally released.
- Released
- 2y ago
- Pricing
- Not published
Specifications
- Developer
- OpenAI
- Series
- Sora
- Family
- Sora 1
- Type
- Video generation
- Predecessor
- —
- Successor
- —
- Released
- February 15, 2024
- Model ID
openai/sora-1- Openness
- Closed
- License
- proprietary
- Input modalities
- text, image, video
- Output modalities
- video
- Modality
- text+image+video->video
- Hugging Face
- —
- Source freshness
- Metadata synced Oct 17, 2026, 5:43 PM UTC
Text 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 explanation