Google · Released 2024-08-01 · v2024-08-01 · Closed · Context 4K tokens
ACTIVEImageGen
Image preference Cap
70
Cadle Image preference Cap 70 · 50%
Arena quality
68
Human preference
Pricing
$0.040
$0.040 / 1M out
CADLE CAP · MEDIA ARENA QUALITY
Image preference Cap is the peer rank for this modality — preference arenas and measured boards (VBench / Open ASR / AA categories) when they exist. Empty axes stay blank; Cap never copies an overall score into realism or motion.
Analysis Media Arena charts (AA Text-to-Image, LMArena I2V, TTS Arena, …) feed this portfolio when the catalog worker has matched this slug. Cards below list Cap axes, arena scores, and evidence sources — not the Language Model Matrix.
IMAGE PREFERENCE CAP · QUALITY AXES
Human preference
68.0
CADLE INSIGHTS
Only measured signals
HUMAN PREFERENCE
68.0
Media Cap quality axis
STRONGEST SIGNAL
Human preference
Cap axis 68.0
BLENDED $/1M
$0.08
In $0.040 · Out $0.040
VALUE INDEX
875.0
Quality ÷ blended $/1M (higher is better)
SPEED · COST · QUALITY
Measured matrix / AA / gateway rows only.
Input $/1M
$0.040
Output $/1M
$0.040
DESCRIPTION + DETAILS
PROVIDER
Google
RELEASE
2024-08-01
CONTEXT
4K tokens
STATUS
ACTIVE
COMMUNITY REVIEWS
OPERATOR NOTES
Quality, latency, cost, and failure modes — not marketing copy.
No reviews yet
WRITE A REVIEW
Tap a star to rate
Stored on this device · synced when signed in
No operator notes yet
First review sets the tone for how teams evaluate Imagen 3.
MODEL COMPARISON
Metric
Imagen 3
Provider
Google
Release
2024-08-01
Input / 1M
$0.04
Output / 1M
$0.04
Context
4K tokens
Cadle Cap
70
Cap board
Cadle Image preference Cap 70
Human preference
68.0
DATA PROVENANCE
Scores may use different scales — check the Benchmarks tab for source links.
Supabase models
Cadle public observations
SOURCE TRACKING
Evidence linked to this model — listing, hub, benchmarks, or live gateway prices.