Model · Pictures

Imagen 4

Google's text-to-picture model, offered to developers in Fast, Standard and Ultra versions through Google's APIs. It has now been retired; Google points people to its newer Gemini image models instead.

Go to Imagen 4’s website

At a glance

Open or closed: Closed
Only usable through the maker's app or API
API-only; no downloadable weights.
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: The terms don't say clearly
Google's API terms were not read; model page does not say.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Cost: No free plan.
Plans below.
How you use it: Maker's own API
Model ids imagen-4.0-generate-001, -fast-generate-001, -ultra-generate-001 on Vertex AI and the Gemini API (both now retired).
source · checked 12 Oct 2026 · checked on the maker's own page
Skill needed: Technical
Inferred: developer API only.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Made by: Google
No legal entity or country stated on the pages read.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Status: No longer available
Gemini API recommends gemini-nano-banana-2.1 as replacement; Vertex AI page recommends gemini-2.5-flash-image (itself due to shut down 2 Oct 2026).
source · checked 12 Oct 2026 · checked on the maker's own page

What you can make with it

A picture, from a description (main use)

text to image

Generation only: no mask editing, outpainting, upscaling or negative prompts.

source · checked 12 Oct 2026 · checked on the maker's own page

Plans and prices

No paid plans listed.

Imagen 4 is absent from the current Gemini API pricing page.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Rights and safety

Watermark: Invisible watermark, Content credentials (C2PA)
Model page lists 'Digital watermarking and verification' and Content Credentials (C2PA).
source · checked 12 Oct 2026 · checked on the maker's own page
Limits: max megapixels: 4.3; max upload mb: 10; note: Max 2816x1536 (Standard, Ultra) or 1408x768 (Fast); up to 4 images per prompt; aspect ratios 1:1, 3:4, 4:3, 9:16, 16:9.
source · checked 12 Oct 2026 · checked on the maker's own page

Replaced by

Gemini 2.5 Flash Image (Nano Banana)

Other options for “A picture, from a description”

Adobe Express, Adobe Firefly, Adobe Photoshop, Akool, Artbreeder, Bria, Canva AI (Magic Studio), ChatGPT Images, Civitai, Clipdrop, ComfyUI, Creatify, DeeVid AI, DiffusionBee, DomoAI, Draw Things, Dreamina, Dzine, fal, Filmora, FlexClip, FLUX.1 [dev], FLUX.1 [schnell], FLUX.1 Kontext

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.