SO

Sora 2

Multimodal modelSora 2

Sora 2

Release date: 2025-09-30Updated: 2026-06-14 23:13:14.9501,889
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
4096
Chinese support
Supported
Reasoning ability

Sora 2 is an AI model published by OpenAI, released on 2025-09-30, for Multimodal model, and 4096 context length, under the 不开源 license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Sora 2

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
4096 tokens
Max output length
4K tokens
Model type
Multimodal model
Modality (in / out)
Text, Image → Video
Release date
2025-09-30
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Sora 2

Open source & experience

Code license
不开源
Weights license
不开源
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Sora 2

Official resources

DataLearnerAI blog
No blog post yet
Sora 2

API details

API speed
1/5
No public API pricing yet.
Sora 2

Benchmark Results

No benchmark data to show.

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Sora 2

Publisher

Sora 2

Model Overview

Sora 2 is an AI model published by OpenAI, released on 2025-09-30, for Multimodal model, and 4096 context length, under the 不开源 license.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code