Skip to content

Google · Video

Veo 3

Google 🇺🇸VideoVeo familyOne of its sources says the weights aren't publicly available.The maker lists this model as deprecated (30 Jun 2026).

Newer version: Veo 3.1. We compared release dates and version names in our catalogue.

From fal.ai's listing:
Veo 3 by Google, the most advanced AI video generation model in the world. With sound on!
llminfo IQ
≈ 89
Maker's price
$0.40 /sec
Max context
1K
Listings
15

Evidence and sources

llminfo IQ ≈ 89, ranked among video generation models. From 41 benchmarks. Little data behind it, so treat it as a rough estimate.How llminfo IQ is computedReleased 26 Jun 2025Maker HQ: US (according to Google's own website)
Sources: LMArena data, Fal.ai data, LiteLLM data, Models.dev data, llminfo researchPrimary data from LMArena from Fal.ai: primary mode, description from LiteLLM: deprecation date from Models.dev: weights availability from llminfo research: release date

Advantages and trade-offs

Compared with 10 video generation models, picked mainly by popularity and IQ

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (30 Jun 2026).

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 4 market median prices.

Input & output

as stated by the model's providers
Text
Images
Video

Capabilities

Supported operations and provider-stated features

Function calling

Listings

 Googlevertex_ai/veo-3.0-generate-001Source: LiteLLM data1K$0.40—
 Cometapiveo3Sources: CometAPI data, CometAPI Pricing dataNot published by the provider$0.40—
 Fastroutergoogle/veo3 · video-standard-1080p-1sSource: FastRouter dataNot published by the provider$0.20—
 Fastroutergoogle/veo3 · video-standard-720p-1sSource: FastRouter dataNot published by the provider$0.20—
 Fastroutergoogle/veo3 · video-audio-1080p-1sSource: FastRouter dataNot published by the provider$0.40—
 Fastroutergoogle/veo3 · video-audio-720p-1sSource: FastRouter dataNot published by the provider$0.40—
 Fastroutergoogle/veo3 · video-standard-4k-1sSource: FastRouter dataNot published by the provider$0.40—
 Fastroutergoogle/veo3 · video-audio-4k-1sSource: FastRouter dataNot published by the provider$0.60—
 NanoGPTveo3-video · duration-8s, no-audioSource: NanoGPTNot published by the provider$0.40$3.20
 NanoGPTveo3-video · audio, duration-8sSource: NanoGPTNot published by the provider$0.60$4.80
 fal.aifal-ai/veo3Sources: Fal.ai data, LiteLLM dataNot published by the provider$0.40—
 fal.aifal-ai/veo3/image-to-video · image-to-videoSources: Fal.ai data, LiteLLM dataNot published by the provider$0.40—

3 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Video generation

VBench 1.062 related benchmarks · 62 results
Source: VBench data docs
BenchmarkScore
VBench 1.0
aesthetic quality
appearance style
background consistency
Show 58 more benchmarksHide 58 benchmarks
BenchmarkScore
color
dynamic degree
human action
imaging quality
motion smoothness
multiple objects
object class
overall consistency
Quality Score
scene
Semantic Score
spatial relationship
subject consistency
temporal flickering
temporal style
VBench 2.0
VBench 2.0 Camera Motion
VBench 2.0 Commonsense Score
VBench 2.0 Complex Landscape
VBench 2.0 Complex Plot
VBench 2.0 Composition
VBench 2.0 Controllability Score
VBench 2.0 Creativity Score
VBench 2.0 Diversity
VBench 2.0 Dynamic Attribute
VBench 2.0 Dynamic Spatial Relationship
VBench 2.0 Human Anatomy
VBench 2.0 Human Clothes
VBench 2.0 Human Fidelity Score
VBench 2.0 Human Identity
VBench 2.0 Human Interaction
VBench 2.0 Instance Preservation
VBench 2.0 Material
VBench 2.0 Mechanics
VBench 2.0 Motion Order Understanding
VBench 2.0 Motion Rationality
VBench 2.0 Multi-View Consistency
VBench 2.0 Physics Score
VBench 2.0 Thermotics
VBench-Long
VBench-Long aesthetic quality
VBench-Long appearance style
VBench-Long background consistency
VBench-Long color
VBench-Long dynamic degree
VBench-Long human action
VBench-Long imaging quality
VBench-Long motion smoothness
VBench-Long multiple objects
VBench-Long object class
VBench-Long overall consistency
VBench-Long Quality Score
VBench-Long scene
VBench-Long Semantic Score
VBench-Long spatial relationship
VBench-Long subject consistency
VBench-Long temporal flickering
VBench-Long temporal style

Human preference

Data credits: LMArena, CC BY 4.0 (licence) · Physical AI Bench (SHI Labs), MIT (licence) · VBench (Vchitect), MIT (licence)

Also known as: fal-ai/veo3, fal-ai/veo3/image-to-video, google/veo-3, google/veo3, veo-3, veo-3-audio, veo-3.0, veo-3.0-generate-001, vertex_ai/veo-3.0-generate-001

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works