Shotcraft
Video generation

Veo 3.1

Generates 4, 6 or 8 second clips with natively generated audio from a text prompt, an image, or up to three reference images.

A video generation model by Google · read 2026-08-14 · sourcing high

Up to
8 seconds
Resolution
4K
Aspect ratios
16:9, 9:16
Weights
Not released
API
Yes
Commercial use
Not established

Supports first-and-last-frame interpolation and extension of an existing generated video. Available via the Gemini API, Google AI Studio, Vertex AI, the Gemini app, Google Vids and Flow.

Commercial use — Not established

The research notes for this model record other terms but do not state a commercial-use position, and no licence page was retrieved, so it is not established here. Check the vendor's own terms.

  • Output is watermarked. All Veo output carries a SynthID watermark

The conditions above were extracted from the licence notes recorded during research, and each one shows the sentence it came from so you can check the reading. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from Google's own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is strong: the figures came from pages we retrieved and read. Check the vendor's current documentation

What it takes in
text, image, video
What it makes
video, audio
Maximum duration
8 seconds
Maximum resolution
4K
Aspect ratios
16:9, 9:16
Controls
image-to-video, keyframes, reference-character-consistency, extend
Weights
Not released
API
Yes
Pricing
Gemini API priced per second of output: $0.40/sec at 720p and 1080p, $0.60/sec at 4K; audio included
Released or updated
2025-10

Strengths

  • Native synchronised audio including dialogue, ambience and music
  • 4K output tier
  • Up to three reference images for subject/style consistency
  • First and last frame specification
  • Video extension supported
  • Available across consumer, developer and enterprise surfaces

Weaknesses

  • Maximum 8 seconds per generation; 1080p and 4K require the full 8s duration
  • Only 16:9 and 9:16 aspect ratios
  • Video extension is limited to 720p
  • Prompt limited to 1,024 tokens; one output video per request
  • Still labelled Preview

Best for

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

MCP servers that front Google

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

Veo 3.1 Fast

Lower-latency, lower-cost variant of Veo 3.1 with the same feature surface: native audio, 4K support, up to three reference images, first/last frame a

Video generation

Veo 3.1 Lite

Cheapest Veo 3.1 tier, capped at 1080p. Unlike the standard and Fast variants it does not support video extension, 4K output, or reference images. Mod

Video generation

Veo 3

Previous-generation Veo model with native audio, superseded by Veo 3.1. Google's Gemini API pricing page marks Veo 3 as deprecated with a scheduled sh

Video generation

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.