Sora Models by OpenAI
OpenAIProprietary
2 models2024–2026
About
Sora is OpenAI's video generation model family, capable of generating high-quality video from text and image prompts.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
2 in view
Sora 2Current
Use when the workload needs video generation and multimodal inputs.
2026-05video generationmultimodal inputs
SoraCurrent
Use when the workload needs video generation and multimodal inputs.
2024-12video generationmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Sora 2 | Use when the workload needs video generation and multimodal inputs. | 2026-05 | video generationmultimodal inputs | Current |
| Sora | Use when the workload needs video generation and multimodal inputs. | 2024-12 | video generationmultimodal inputs | Current |
Release Timeline
2 release groupsSpecifications(2 models)
Frequently Asked Questions
- What is Sora used for?
- Sora is used for video generation and vision and multimodal work. The family description and listed model capabilities point to those workloads as the best fit.
- How does Sora compare to GPT Realtime 2?
- Sora by OpenAI is strongest where you need video generation, while GPT Realtime 2 by OpenAI is the closest related family to check for translation. Sora has 2 listed variants, while GPT Realtime 2 reaches up to 131K context, so compare the specs and pricing tables before choosing a production model.
- Which Sora model should I use?
- If price is the main constraint, use the pricing table first because Sora does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Sora 2 with multimodal inputs.
