Sora 2 Pro
Sora 2 Pro is a flagship video generation model from OpenAI that accepts text, image, and video inputs to produce video output.
OpenAIOpenAI flagship video generation from text and images
Sora 2 Pro is a video generation model developed by OpenAI, released in September 2025. It accepts text prompts, reference images, and character reference videos as inputs, and generates video output at a cost of $0.30–$0.50 per second of generated video. The model supports a context window of 5,000 tokens and is tagged as a flagship offering within OpenAI's model lineup.
Sora 2 Pro is designed for use cases that require generating video from descriptive text or image inputs, including character-consistent video creation using named character references. Its input schema includes configurable duration and resolution size options, making it adaptable to different production requirements. The model is available as a first-party provider on MindStudio, with no separate API key setup required to use it within the platform.
What Sora 2 Pro supports
Text-to-Video Generation
Generates video clips from natural language text prompts. Supports a context window of up to 5,000 tokens for prompt input.
Image-to-Video
Accepts a reference image URL as input and animates or extends it into a video sequence.
Character Reference Video
Takes a character reference video URL and a character name to maintain consistent character appearance across generated video output.
Configurable Duration
Allows users to select the desired length of the generated video via a duration parameter at generation time.
Resolution Size Selection
Supports selectable output resolution sizes, giving control over the dimensions of the generated video.
Ready to build with Sora 2 Pro?
Get Started FreeCommon questions about Sora 2 Pro
What is the context window for Sora 2 Pro?
Sora 2 Pro supports a context window of 5,000 tokens, which applies to the text prompt input used to describe the video to be generated.
How much does Sora 2 Pro cost to use?
Sora 2 Pro is priced at $0.30 to $0.50 per second of generated video output. The exact rate may vary depending on the selected resolution or duration settings.
What input types does Sora 2 Pro accept?
Sora 2 Pro accepts text prompts, image URLs, and character reference video URLs. It also includes selectable parameters for video duration and output size.
When was Sora 2 Pro released?
Sora 2 Pro was released in September 2025 by OpenAI.
Can Sora 2 Pro maintain consistent characters across a video?
Yes. Sora 2 Pro includes a character reference input that accepts a video URL and a character name, which is used to maintain visual consistency for that character in the generated output.
Parameters & options
Optional URL of an input image to animate. Must be the exact dimensions as the video output.
(Optional) Upload a 2-4 second video of objects, animals, or animated characters as references to appear within your videos to maintain recognizable mascots and products across campaigns and creative assets.
(Optional) Name for the character (must be mentioned in the prompt)
Explore similar models
OpenAISora 2
Sora 2 is a video generation model from OpenAI that creates videos from text prompts, images, and character references.
OpenAIGPT-6 Astra
OpenAIGPT Realtime 2.1
ByteDanceSeedance 2.0 Fast Turbo
Seedance 2.0 Fast Turbo is a video generation model from ByteDance that supports text-to-video and image-to-video workflows.
WanWan 2.7
Wan 2.7 is a video generation model supporting text-to-video and image-to-video creation with audio and reference image inputs.
GoogleVeo 3.1
Veo 3.1 is a Google video generation model that creates videos from text prompts or images, with optional audio output.
Start building with Sora 2 Pro
No API keys required. Create AI-powered workflows with Sora 2 Pro in minutes — free.