Sora dropped to ChatGPT Plus and Pro users in Dec 2024 after early tests in Feb.
It handles text‑to‑video, image‑to‑video and video remix. Text-to-video works better than image-to-video.
Makes videos up to 60 seconds in 1080p or portrait mode like 1080×1920.
Takes in varied sizes and lengths using a patch‑based setup with latent encoding.
Known for real‑looking clips that match prompts with smooth motion and camera moves.
Still struggles with stuff like physics hands and scenes with many characters. It was added into ChatGPT by Feb 2025 and became available in Europe and UK then too.
Sora v1 - a placeholder designation for the first publicly released Sora video generation model by OpenAI. This version naming is internally assigned for reference, as no official model name was provided by the OpenAI.
If you'd like to access this model, you can explore the following possibilities:
Use our video cost calculator to compare prices between platforms offering Sora model.
For locally hosted models, see description and additional links at the bottom for versions, repos and tutorials.
