Last updated: 16/04/2025

Google Vertex AIOfficial Docs

Imagen 3.0 002 model

imagen-3.0-generate-002

active

Imagen 3.0 002 model

The Imagen 3.0 002 model from Google is a powerful AI capable of generating, editing, and customizing images based on text prompts. With a 480 token context window, it supports a wide range of inputs and outputs including text, image, video, audio, transcription, and text-to-speech. This model is well-suited for various applications and can be fine-tuned for custom needs.

Supports a 480 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications.

Additional Information

Notes

This is the Imagen 3.0 model for image generation. According to the pricing documentation, it costs $0.04 per image. The model supports text-to-image generation in English, Chinese, Hindi, Japanese, Korean, Portuguese, and Spanish.

Model Timeline

Launch Date

2/25/2025

Capabilities

Text

Input Pricing

$0.04/ image

Context: 480 tokens

Output Pricing

$0.04/ image

Vision Capabilities

Image

Generation Pricing

$0.04 /image

Embeddings

Embeddings Pricing

$0.0002/1k tokens

Flatten your repo for AI in seconds

Flatten repos. Prompt faster. One click → one GPT-ready file

Free Online & Desktop