Models / Google
Video

Google Veo 3.0

Next-generation Google video AI

About model

Google Veo 3.0 represents the latest advancement in Google's video generation technology with extended duration.

Quickstart guides
  • API usage

    • cURL
    • Python
    • Typescript

    Endpoint:

    google/veo-3.0

    curl --request POST \
      --url https://api.together.xyz/v2/videos \
      --header "Authorization: Bearer $TOGETHER_API_KEY" \
      --header "Content-Type: application/json" \
      --data '{
        "model": "google/veo-3.0",
        "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="google/veo-3.0"
    )
    
    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: "google/veo-3.0"
      });
    
  • Model card

    Architecture:
    • Third-generation Veo
    • Extended 8-second output
    • Enhanced quality

  • Applications & use cases

    Use Cases:
    • Extended video clips
    • Story-driven content
    • Creative productions

Related models
  • Model provider
    Google
  • Type
    Video
  • Main use cases
    Text-to-Video
    Image-to-Video
  • Resolution/Duration
    720p / 8s
  • Deployment
    Serverless
  • Input price

    $1.60 / video

  • Input modalities
    Text
    Image
  • Output modalities
    Video
  • Released
    October 7, 2025
  • Last updated
    October 20, 2025
  • Category
    Video