Veo 3.1 Audio
Google
Key facts · verified Oct 14, 2026
Veo 3.1 Audio is a Google video generation model released on 17 Nov 2025. Pricing: $0.40 per second (720p, 1080p), $0.60 per second (4K) via the Gemini API (Gemini API preview codes shut down 22 October 2026). It ranks #12 on LMArena's text-to-video leaderboard (Elo 1364, read 1 Nov 2026). Source: docs.cloud.google.com.
Google's Veo 3.1 video model (veo-3.1-generate-001), generally available on Vertex AI since 17 November 2025. It generates 4-, 6- or 8-second clips at up to 4K and 24 fps from text, an image, or a first and last frame, and generates sound in the same pass.
Pricing & specs checkedSource: vendor documentation · checked Oct 14, 2026LMArena: 1364 Elo (rank 12) · source · retrieved Nov 1, 2026
Pricing
$0.40 per second (720p, 1080p), $0.60 per second (4K) via the Gemini API (Gemini API preview codes shut down 22 October 2026)
Context
Not published
LMArena Elo
LMArena rank
Key Features
Video Generation
Full Specifications
$0.40 per second (720p, 1080p), $0.60 per second (4K) via the Gemini API (Gemini API preview codes shut down 22 October 2026) | |
|---|---|
| Identity | |
| Developer | |
| Released | Nov 2025 |
| Status | GA. Retirement date: November 17, 2026 or later |
| Cost | |
| Price per second | $0.40 (720p, 1080p), $0.60 (4K) — Gemini API standard |
| Capacity | |
| Max duration | 8 seconds (4, 6 or 8) |
| Max resolution | 4K (outputs 720p, 1080p, 4K) |
| FPS | 24 |
| Capability | |
| Text-to-video | Yes |
| Image-to-video | Yes, including first and last frame |
| Native audio | Yes |
| Access | |
| API | Yes — Gemini API and Vertex AI |
| Measured quality | |
| LMArena Elo | 1364 (checked Nov 2026) |
| LMArena rank | Rank 12 |