Sora

OpenAI

DISCONTINUED. OpenAI's original text-to-video diffusion model, announced February 2024 (public release December 2024 as 'Sora Turbo'). Generated videos up to one minute long using a transformer architecture that represents video as patches. Superseded by Sora 2; the entire Sora product is being discontinued (app/web ended April 26, 2026; API ends September 24, 2026).

Strengths

Generated up to one-minute videos - longest among early text-to-video models
Transformer/patch architecture enabled superior scaling and quality
Deep language understanding for accurate prompt interpretation
Multi-shot capability with persistent characters and visual style

Caveats

DISCONTINUED - superseded by Sora 2; Sora product ending in 2026 (app ended Apr 26 2026)
Proprietary model - no self-hosting or customization
High computational requirements for minute-long video generation

Vendor: OpenAI
License: Proprietary
Release Date: 2024-02-15
Modalities: text
video

Capabilities

Vision

Audio

Video

Tool Use

Resources

API Documentation

Pricing

Discontinued. Was available to ChatGPT Plus/Pro subscribers; superseded by Sora 2 (Sora product ending 2026).