OpenAI · 2026

Sora 2

8.8Video model

CompanyOpenAI

Release2026

TypeVideo model

Context windowN/A

Input typesText, Image

Output typesVideo, Audio

ReasoningN/A

CodingN/A

MultimodalYes

API availableYes

PricingIn ChatGPT plans

Overview

Sora 2 is a video model model from OpenAI, released in 2026. It accepts text, image as input and produces video, audio. With a context window of N/A, it is well suited to state-of-the-art video generation.

Capabilities

On reasoning, Sora 2 is rated n/a, while its coding ability is n/a. Multimodal support: Yes. These characteristics make it a strong fit for state-of-the-art video generation. As with any frontier system, real-world performance depends heavily on how you prompt and integrate it.

Availability & Pricing

Sora 2 is accessible via an API. Pricing model: In ChatGPT plans. Availability and pricing for AI models change frequently; confirm the latest details from OpenAI before building on it.

Best Use Cases

The sweet spot for Sora 2 is state-of-the-art video generation. Teams choosing a model should weigh context length, cost, latency and modality against their workload — Sora 2 is a particularly good match when those priorities align with its strengths.