Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Google / Veo

Veo 3.1 Generate 001

Enterprise standard video-generation release with sound, frame interpolation and video extension listed in its model card.

Video generation
availableClosed weightsVideo generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
18 of 29 specification fields collected
Output resolution720p, 1080p, 4KSee specification notes below
Clip duration4, 6 or 8 secondsSee specification notes below
Input billingSee ratesGoogle Enterprise Agent Platform
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Input token limit
Not collected
Maximum output
Not collected
Input modalities
Text, ImageSource for Input modalities (opens in a new tab)

Video input appears separately through the extension capability, despite the modality table describing video as output-only.

Output modalities
Video, AudioSource for Output modalities (opens in a new tab)

Sound generation is explicitly supported.

Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not supportedSource for Batch processing (opens in a new tab)
Fine-tuning
Not collected
Context caching
Not collected
Architecture
Not collected
Parameters
Not collected
Knowledge cutoff
Not collected
Languages
EnglishSource for Languages (opens in a new tab)
Release date
2025-11-17Source for Release date (opens in a new tab)
Video duration
4, 6 or 8 secondsSource for Video duration (opens in a new tab)

Reference-image-to-video requests require 8 seconds.

Videos per request
Up to 4 videos per promptSource for Videos per request (opens in a new tab)
Image input limits
20 MB input image maximum; 720p or 1080p input resolutionSource for Image input limits (opens in a new tab)
Output resolutions
720p, 1080p, 4KSource for Output resolutions (opens in a new tab)
Frame rate
24 FPSSource for Frame rate (opens in a new tab)
Aspect ratios
9:16, 16:9Source for Aspect ratios (opens in a new tab)
Output formats
MP4Source for Output formats (opens in a new tab)
Published availability regions
us-central1Source for Published availability regions (opens in a new tab)
Video extension
SupportedSource for Video extension (opens in a new tab)

Enterprise card; do not overwrite different Developer preview behavior.

Reference images
SupportedSource for Reference images (opens in a new tab)

Asset reference images supported; exact maximum number not established here.

Frame controls
First and last frame interpolationSource for Frame controls (opens in a new tab)
Quality and watermark controls
C2PA content credentials supportedSource for Quality and watermark controls (opens in a new tab)
Request quotas
Quota label says prediction requests per minute, but value says 50 tokens per minute; exact quota unit unresolved.Source for Request quotas (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Google Enterprise Agent Platform

Provider source (opens in a new tab)
API model ID
veo-3.1-generate-001
Access
Google Cloud project with billing, IAM and Agent Platform API enabled. Model card lists Provisioned Throughput and fixed-quota consumption; PayGo is marked unsupported. GA.
Regions
us-central1
Batch processing
Not supportedSource for Batch processing (opens in a new tab)
provisionedThroughput
SupportedSource for provisionedThroughput (opens in a new tab)
payAsYouGo
Not supportedSource for payAsYouGo (opens in a new tab)
fixedQuota
SupportedSource for fixedQuota (opens in a new tab)
audioInput
Not supportedSource for audioInput (opens in a new tab)
Image preparation
SupportedSource for Image preparation (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Video generation: billing unit needs verification720p / 1080p with audio1$0.40provider billing count (unit unresolved)
Video generation: billing unit needs verification4K with audio1$0.60provider billing count (unit unresolved)
Video generation: billing unit needs verification720p / 1080p without audio1$0.20provider billing count (unit unresolved)
Video generation: billing unit needs verification4K without audio1$0.40provider billing count (unit unresolved)

Rate conditions

  1. The pricing page states this family/resolution rate per count, without a defined count unit. No token or per-clip conversion is made. Model-card access constraints apply.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Google Enterprise Agent Platform

veo-3.1-generate-001
Not verified

No verified cache policy for this exact model; generic Gemini prompt caching is not assumed.

How it works
Not collected

No verified cache policy for this exact model; generic Gemini prompt caching is not assumed.

Minimum reusable input
Not collected

No verified cache policy for this exact model; generic Gemini prompt caching is not assumed.

Lifetime & refresh
Not collected

No verified cache policy for this exact model; generic Gemini prompt caching is not assumed.

How to enable it
Not collected

No verified cache policy for this exact model; generic Gemini prompt caching is not assumed.

Usage fields
Not collected

No verified cache policy for this exact model; generic Gemini prompt caching is not assumed.

Billing rules
Not collected

No verified cache policy for this exact model; generic Gemini prompt caching is not assumed.

Limits & data boundaries
Not collected

No verified cache policy for this exact model; generic Gemini prompt caching is not assumed.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Google publishes this named proprietary hosted release and selector without downloadable weights. This is a version-level catalog record, not a claim of a new base architecture or distinct weights from another host or preview. No explicit selector-alias equivalence is established in the reviewed card.

Classification evidence (opens in a new tab)

Lifecycle dates

Enterprise release17 Nov 2025Source (opens in a new tab)
Earliest possible Enterprise retirement17 Nov 2026Source (opens in a new tab)

Sources reviewed