Gemini

Veo 3.1

GeminiSpecialized
Vision

About this model

Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio —...

Performance Tier

Specialized

Veo 3.1 is a specialized model from Gemini : built for a specific domain.

Domain-specific model. Optimized for a particular task such as code generation, image creation, or web search.

Pricing

This model is included in Elosia plans
Premium

Highest cost level. A long conversation can quickly use up your included usage or your balance.

Capabilities

Context Length—
Max Output Tokens—
Inputtext, image
Outputvideo
Release DateMarch 23, 2026

Recommended Use Cases

Creative Writing

Strengths

  • Up to 4K output, resolution selectable per generation
  • Native audio generation with strong lip-sync and ambient sound
  • Built on DeepMind research, with motion and physics simulation as an explicit design focus
  • Fixed 4, 6 or 8 second durations optimized for quality over length

Limitations

  • Maximum clip length of eight seconds per generation, so longer sequences must be assembled from several runs
  • Durations are fixed to four, six or eight seconds, with no intermediate value

Frequently asked questions

Resources

This model may use your data for training

Similar Models