← Models

Sora 2

OpenAI · Sora

Base Sora 2 API video tier retained for compatibility during OpenAI's announced Sora sunset window.

Part of Sora family · Other versions: Sora 2 Pro
Type
video
Context
N/A
Max Output
N/A
Status
deprecated
API Access
Yes
License
proprietary
video-generation text-to-video image-to-video openai creative
Released September 2025 · Updated June 8, 2026

Overview

Freshness note: Model capabilities, limits, and availability can change quickly. This profile is a point-in-time snapshot last verified on June 8, 2026.

Sora 2 is the base API tier in OpenAI’s Sora family for video generation from text and image inputs. It is now a deprecated/sunset-route page: OpenAI says the standalone Sora app/web experience was discontinued on April 26, 2026, and the Sora API will be discontinued on September 24, 2026. Existing users can still use this page for compatibility and migration planning while the developer docs remain live.

Capabilities

Sora 2 is designed for prompt-driven video synthesis with synced audio and support for iterative creative direction. In practice, it is now most relevant for teams that already built workflows around Sora and need to decide which shots, prompts, and budgets should migrate elsewhere.

That makes it useful for short-term motion ideation, campaign concept testing, rough-cut planning, storyboard validation, and output comparisons against active alternatives.

Technical Details

Sora 2 is video-native, so token-based context and output limits are not the primary published constraints. In this repository, contextWindow and maxOutput are intentionally set to 0 and interpreted as N/A.

OpenAI’s current model docs position Sora 2 as the base synced-audio API route, with sora-2-pro above it for higher-fidelity generations and larger output dimensions. The same planning must account for the announced September 24, 2026 API discontinuation.

Pricing & Access

OpenAI publishes Sora Video API pricing directly on its API pricing page. The base sora-2 tier is listed at $0.10 per second for 720p portrait or landscape output. Higher-fidelity work routes to sora-2-pro, which costs more per generated second and supports larger output formats.

Product-surface quotas still vary, so teams should separate API budgeting from ChatGPT and Sora-app allowance assumptions.

Best Use Cases

Best for existing short-form concept videos, storyboard-to-motion iteration, ad creative previsualization, and migration comparisons where teams need to understand how a lower-cost OpenAI video route maps to current alternatives.

Comparisons

Compared with Sora 2 Pro, Sora 2 is the cheaper compatibility tier, while Pro is the fidelity upgrade. Compared with Veo 3.1 or Runway Gen-4.5, Sora 2 now needs to be evaluated through sunset risk as much as quality. Compared with grok-imagine-video, Sora 2 remains an OpenAI-stack reference point, but not a fresh default.