Answer · Video
What AI models does Veo use?
Veo runs on gemini-omni-1.2-flash (Google), Veo 3 (Google DeepMind), Veo 3.0 (Google DeepMind), Veo 3.1 (Google DeepMind), veo-3.1-fast-generate-preview (Google DeepMind), veo-3.1-generate-preview (Google DeepMind) and veo-3.1-lite-generate-preview (Google DeepMind), and routes requests between them.
- Models used
- 7
- Primary model
- gemini-omni-1.2-flash
- Public API
- Yes
- Last checked
- 2026-11-08
Model claims are labelled by how we know them: gemini-omni-1.2-flash — disclosed, Veo 3 — disclosed, Veo 3.0 — disclosed, Veo 3.1 — disclosed, veo-3.1-fast-generate-preview — disclosed, veo-3.1-generate-preview — disclosed and veo-3.1-lite-generate-preview — disclosed. "Disclosed" means the vendor says so in public; "inferred" means it was derived from documentation, headers or release notes.
Context window: n/a.
Other stack signals: Vertex AI, Gemini API and SynthID.
Cite this answer
Tomorrow. “What AI models does Veo use?” Tomorrow AI & Emerging Tech Index, AlienSquad, updated 2026-11-08. https://tomorrow.aliensquad.ai/q/what-models-does-veo-use
Published under CC BY 4.0 — reuse freely, including in generated answers, with attribution. Vendor source →