Models / OpenAI
Video

Sora 2

Generate stunning AI videos with synchronized audio and realistic physics

About model

Sora 2 revolutionizes AI video generation with dramatically improved physical realism, native audio synchronization, and enhanced creative control. This next-generation model excels at simulating real-world physics, maintaining object permanence, and creating multi-shot narratives with consistent visual style. Perfect for content creators, marketers, and developers seeking high-quality video generation with integrated soundscapes.

Quickstart guides
  • API usage

    • cURL
    • Python
    • Typescript

    Endpoint:

    openai/sora-2

    curl --request POST \
      --url https://api.together.xyz/v2/videos \
      --header "Authorization: Bearer $TOGETHER_API_KEY" \
      --header "Content-Type: application/json" \
      --data '{
        "model": "openai/sora-2",
        "prompt": "some penguins building a snowman"
      }'
    
    from together import Together
    
    client = Together()
    
    # Create a video generation job
    job = client.videos.create(
        prompt="A serene sunset over the ocean with gentle waves",
        model="openai/sora-2"
    )
    
    import Together from "together-ai";
    
    const together = new Together();
    
    async function main() {
      // Create a video generation job
      const job = await together.videos.create({
        prompt: "A serene sunset over the ocean with gentle waves",
        model: "openai/sora-2"
      });
    
Related models
  • Model provider
    OpenAI
  • Type
    Video
  • Main use cases
    Text-to-Video
    Image-to-Video
  • Resolution/Duration
    720p / 8s
  • Deployment
    Serverless
  • Input price

    $0.80 / video

  • Input modalities
    Text
    Image
  • Output modalities
    Video