How does Imagen 4 pricing work?

Credit-based: 1 credit equals $0.001 USD. Imagen 4 is a flat per-image rate regardless of aspect ratio. The schema fixes n at 1, so total charge equals one image per call. See current rate in the pricing table on this page. Failed Imagen 4 tasks are refunded automatically — you only pay for successful renders.

What aspect ratios does Imagen 4 support?

Five ratios via the size field: 1:1 (square), 4:3 and 3:4 (editorial), 16:9 and 9:16 (hero / mobile). The default is 16:9. Passing a ratio outside this set returns a 400 — Imagen 4 on reApi rejects unsupported values explicitly so you catch the bad input client-side instead of getting a silent fallback.

Does Imagen 4 support image-to-image?

No. Imagen 4 is text-to-image only — image_urls, mask, and similar reference fields are rejected. For image-to-image with reference fusion, use seedream-5-0-lite (flat per-image, multi-reference) or the gemini-3-pro-image-preview family (multi-tier resolution).

Can I generate multiple images in one Imagen 4 call?

Imagen 4's spec accepts only n = 1 per request. To produce variations, send multiple parallel requests — the async task model is designed for exactly this; each task_id polls independently and the per-image cost is identical.

How long are Imagen 4 output URLs valid?

Image URLs returned by Imagen 4 are valid for 24 hours from completion. For longer retention, download the asset and re-host on your own storage (R2 / S3 / OSS) as soon as your worker receives the completion event.

Where is the full Imagen 4 API reference?

The complete parameter list, validation rules, error codes, and runnable examples for Imagen 4 live at /docs/imagen-4-0.

Is Imagen 4 API free or paid?

Paid. Completed generations are charged at the rates in this page's pricing table. Eligible new accounts may receive promotional test credits; availability and amount are shown at signup or in the dashboard. Technical or provider failures are refunded automatically, except where this page documents a charged output-moderation block.

Does Imagen 4 API require a monthly subscription?

No. Pricing is pay-as-you-go: $1 buys 1,000 credits and credits never expire. Cost scales with what you generate rather than with a recurring fee.

How do I get a Imagen 4 API key?

Sign up and create a key in the dashboard, no card required. Pass it as a Bearer token in the Authorization header.

Imagen 4 API — Google Imagen 4.0 Text-to-Image

Imagen 4.0 is Google's flagship text-to-image model. Five aspect ratios, one flat per-image rate, async-first JSON contract — drop it into the same /api/v1/images/generations endpoint you already use.

Highlights: Google Imagen 4 · 5 aspect ratios
Best for: Photoreal stills, typography, product art
Input: Text prompt
Output: One image per request

Input

Prompt*

English or Chinese · detailed prompts produce better Imagen 4 results

Aspect ratio

1:1 · 4:3 · 3:4 · 16:9 · 9:16 — pick by surface

Count

Fixed at 1 on Imagen 4 — send multiple requests for variations

Estimated cost~$0.04646 credits

Result

Try one of these prompts

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

First test cost

$0.04646 credits

One sample at the cheapest tier (1 image).

Testing budget guide

Add credits

$10

≈ 217 tests

$50

≈ 1086 tests

$100

≈ 2173 tests

Any aspect ratio: $0.046; Price · 1 image

What is the Imagen 4.0 API?

Imagen 4.0 is Google's high-fidelity text-to-image model — prompts only, with no reference images and no inpainting masks. Each request takes a prompt of up to 4,000 characters and one of five aspect ratios (1:1, 4:3, 3:4, 16:9, 9:16, default 16:9), returns exactly one image, and is billed at a flat per-image rate.

Imagen 4 sample renders across five aspect ratios

What you can build with this model

Real-world workflows and production use cases you can build and ship with this model.

Hero shots at any aspect ratio

Imagen 4 covers the five aspect ratios most product surfaces ship — 1:1 for grid tiles, 16:9 and 9:16 for hero / mobile, 4:3 and 3:4 for editorial. One prompt template, five ratios, one flat rate. The same scene description carries across ratios without recomposition, which keeps a campaign visually consistent across web, app, and social.

Generate a hero

Editorial and marketing creative

Imagen 4's prompt adherence and lighting handle editorial-grade product photos, marketing banners, and brand moodboards. Describe the subject, the surface, the light, the lens — the render lands with composition you can drop straight into a layout. Async submit returns a task_id in milliseconds so a creative pipeline isn't blocked waiting on render.

Concept art and ideation

Send Imagen 4 a free-form scene description — a city skyline, a character beat, a landscape under a specific light — and it returns a single high-fidelity frame. Because Imagen 4 is text-to-image only, the result is purely prompt-driven; ideal for early-stage concept work where you haven't picked a reference yet.

Why reAPI for Imagen 4.0

Google Imagen 4 on one endpoint

Imagen 4 ships through the same /api/v1/images/generations endpoint you already use for the rest of your image stack. One JSON shape, one auth header, one credit ledger. Send model: imagen-4-0 with a prompt and a size and the task lands the same way every other reApi image task does.

Flat per-image rate — no hidden tiers

1 credit equals $0.001 USD. Imagen 4 is a flat per-image rate regardless of aspect ratio. No quality tier, no resolution tier, no n multiplier — the spec accepts exactly one image per request. The estimator on this page is the actual charge.

Async-first for production stacks

Submit an Imagen 4 task, get a task_id back, poll until done. Failed and moderated requests are not charged. Imagen 4 fits the same task plumbing as every other reApi model — drop it in, the lifecycle is identical.

Integrate Imagen 4 in three steps

step 01
Create an API key
Sign up at reApi and grab a key. Free signup credits cover dozens of Imagen 4 generations, enough to validate the prompt → asset path before topping up.
Open
step 02
Submit a generation
POST to /api/v1/images/generations with model: imagen-4-0, a prompt, and an optional size. Imagen 4 returns a task_id immediately — your handler is free to move on.
Open
step 03
Poll the result
GET /api/v1/tasks/:id until status is completed. The Imagen 4 response carries an image URL valid for 24 hours; mirror to your own storage if you need it longer.
Open

docs/api/imagen-4-0

API reference

Drop-in code and the full parameter table.

View full reference

curl -X POST https://reapi.ai/api/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "imagen-4-0",
    "prompt": "A corgi wearing an astronaut helmet on the lunar surface",
    "size": "16:9"
  }'

Parameter validation failed

Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.

Authentication or balance issue

401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.

Content or material rejected

Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.

Task failed or timed out

A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.

Frequently asked questions

Common questions about this model.

Imagen 4 is Google's flagship text-to-image model. It renders at five aspect ratios — 1:1, 4:3, 3:4, 16:9, 9:16 — and accepts English or Chinese prompts. On reApi it ships as model id imagen-4-0 on the unified /api/v1/images/generations endpoint, billed at a flat per-image rate. See current rate in the pricing table on this page.