Imagen 3.0 Ultra

NEW HOT

Google · Gemini

API

Google's flagship text-to-image model, excelling in high-fidelity, photorealistic, and complex long-context image generation with basic video synthesis.

TextVisionVideo

Scores 82% on MMLU, competitive across 4 standard benchmarks.

Data aggregated and editorially reviewed by TrendMing.

Benchmark Performance

MMLU82%
HumanEval45%
MATH38%
GPQA72%

Scores sourced from published evaluations. Higher = better.

Quick Specs

Context Window16K tokens
Parameters900B
Input pricing$0.015 / 1K tokens
Output pricing$0.04 / image
Released2026-06-20