Sponsored by Byond Boundrys Consulting - Empowering Ideas, Delivering Results
OpenAI Intermediate

Sora 2

Sora 2 is OpenAI's legacy synced-audio video model, still available through the Videos API at $0.10 per generated second for listed 720p output.

Video GenerationTextImageAudioVideo Freemium
In plain English

What is this model and why does it matter?

Sora 2 is OpenAI's legacy synced-audio video model for generating clips from text or images.

Short video generationSynced-audio clipsStoryboardsCreative media prototypesImage-to-video
Model overview

Sora 2: features, use cases and important details

Sora 2 is OpenAI’s video-and-audio generation model introduced in September 2025.

Verified model facts

OpenAI documents text and image input, synchronized video/audio output and current API pricing of $0.10 per generated second for 720×1280 portrait or 1280×720 landscape.

Current status

The model remains callable through the Videos API, but OpenAI’s current model page labels it Legacy.

Best fit

It is suitable for short creative clips, storyboards, image-to-video animation and media prototypes.

Limitations

As a legacy model it is not the best assumption for new long-lived integrations, and generated video can contain continuity, physics or detail errors.

Get started

How to use this model

  1. Create an OpenAI API key.
  2. Submit text or image input to the Videos API using model sora-2.
  3. Choose supported orientation/resolution.
  4. Poll for completion and retrieve the video.
  5. Use newer media models when OpenAI recommends migration from this legacy model.
Copy and try

Example prompts

  • Generate a cinematic 8-second shot of a rainy neon street with synchronized ambient audio.
  • Animate this image into a short product reveal with natural sound.
Capabilities

What it can do

  • Text-to-video
  • Image-to-video
  • Synchronized audio
  • Dynamic short clips
Best for

Practical use cases

  • Creative video
  • Advertising concepts
  • Storyboards
  • Social media prototypes
Pricing

What does it cost?

$0.10 per generated video second for 720x1280 portrait or 1280x720 landscape output on the current Sora 2 API model page.

Simple summaryCurrent Sora 2 API pricing is $0.10 per generated second at its listed 720p portrait/landscape resolution.

What stands out

  • Synced audio
  • Official API
  • Simple per-second pricing
  • Text and image input

Things to consider

  • OpenAI labels it Legacy
  • Higher-resolution work requires Sora 2 Pro or newer options
  • Not open source
Limitations

Important restrictions and trade-offs

  • Legacy lifecycle means new projects should watch for replacement guidance
  • Video generation can produce physical or continuity errors
  • Usage is safety-filtered
SimplifyAITools verdict

Our editorial take

Still usable through the API, but classify it as a legacy/deprecated generation and avoid presenting it as OpenAI’s newest video model.

References

Primary sources

  1. Open source 1 ↗
  2. Open source 2 ↗
  3. Open source 3 ↗
Keep exploring

Related AI models