← Models

Sora 2 Pro

OpenAI · Sora

Premium Sora 2 Pro API tier retained for compatibility during OpenAI's announced Sora sunset window.

Part of Sora family · Other versions: Sora 2
Type
video
Context
N/A
Max Output
N/A
Status
deprecated
API Access
Yes
License
proprietary
video-generation synced-audio text-to-video image-to-video creative openai
Released October 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 Pro is OpenAI’s higher-end video-generation route above the base Sora 2 tier. 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, cost modeling, and migration comparisons while the developer docs remain live.

The model is relevant for campaign previsualization, premium concept films, higher-stakes brand work, and product teams that need to map stronger Sora outputs to active alternatives before the sunset date.

Capabilities

Sora 2 Pro generates video from natural-language or image prompts and includes synced audio output. The practical difference versus Sora 2 is not just that it costs more. OpenAI positions Pro as the route for richer detail, tougher prompts, and more advanced media generation where you want fewer compromises on the first strong pass.

That makes it useful for migration comparisons around cinematic previs, ad creative development, narrative mockups, and audio-aware short-form generation where prompt fidelity matters. It is still best thought of as a generative ideation and production-assist tool, not a replacement for full editorial control.

Technical Details

Sora 2 Pro is video-native, so token-style context and max-output fields are not meaningful in the same way they are for language models. In this repository, contextWindow and maxOutput are intentionally stored as 0 and should be interpreted as N/A.

OpenAI’s current docs show multiple output pricing tiers for Pro:

  • 720x1280 portrait / 1280x720 landscape
  • 1024x1792 portrait / 1792x1024 landscape
  • 1080x1920 / 1920x1080-class output

The model accepts text and image inputs, and produces video plus audio output.

Pricing & Access

Current API pricing is per generated second:

  • Standard resolution: $0.30 / second
  • Higher resolution: $0.50 / second
  • 1080p-class output: $0.70 / second

API and product-surface assumptions should be treated separately when budgeting. The important current planning point is the announced Sora API discontinuation on September 24, 2026.

Best Use Cases

Choose Sora 2 Pro only for existing workflows, sunset-window compatibility, or migration comparisons that need higher-fidelity Sora outputs. For fresh video-generation work, evaluate active alternatives before building around Sora.

Comparisons

  • Sora 2 (OpenAI): Cheaper base compatibility tier; Pro is the fidelity upgrade.
  • Veo 3.1 (Google): Strong active competing route where tradeoffs often come down to provider ecosystem, controls, and motion style.
  • Runway Gen-4.5 (Runway): Active creative-video route to evaluate when continuity and production tooling matter.