---
title: "Imagen 4 API — All variants, pricing, code samples | RunAPI"
url: "https://runapi.ai/models/imagen-4.md"
canonical: "https://runapi.ai/models/imagen-4.md"
locale: "en"
model: "Imagen 4"
provider: "Google"
modality: "image"
variant_count: 4
price_from_cents: 4
---

# Imagen 4

Photorealistic text-to-image with precise typography, broad style range, and up to 2K resolution.

**Provider:** Google
**Modality:** Image
**Catalog:** 4 variants

Imagen 4 is Google's photorealistic image generation model with strong typography rendering and support for resolutions up to 2K. It produces detailed, true-to-life images with accurate color and lighting.

## Variants

| Version | Variant | Pricing | Billing | URL |
|---|---|---|---|---|
| imagen-4 | `imagen-4` | $0.080 | call | https://runapi.ai/models/imagen-4/imagen-4.md |
| imagen-4-fast | `fast` | $0.040 | call | https://runapi.ai/models/imagen-4/fast.md |
| imagen-4-pro-image-to-image | `pro-image-to-image` | $0.180 | call | https://runapi.ai/models/imagen-4/pro-image-to-image.md |
| imagen-4-ultra | `ultra` | $0.120 | call | https://runapi.ai/models/imagen-4/ultra.md |


## Install

```sh
npm install @runapi.ai/imagen-4
# or
gem install runapi-imagen_4
```

## Quickstart

```sh
curl -X POST https://runapi.ai/api/v1/imagen_4/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "imagen-4", "prompt": "..." }'
```

## Context

Imagen 4 is Google's latest text-to-image model, delivering photorealistic results with broad style support. Through RunAPI, all Imagen 4 variants — standard, fast, ultra, and pro — share one API key.

## FAQ

### Which variant should I start with?

Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.

### Is there a free tier?

New accounts get free first calls on every model. After that, pay per call.

### Do you stream results?

Where streaming is available, RunAPI streams end-to-end.

### How are failures billed?

Failed generations are not charged.

### Are outputs cached?

Generated outputs are stored and retrievable by task ID. Inputs are not cached.

### Can I use commercially?

Yes — commercial use is included for every variant unless a model license explicitly restricts it, which is called out on the variant page.

### What about rate limits?

Per-key rate limits scale with usage tier. See pricing page for current limits.

### Where can I report issues?

Open an issue on the public GitHub repo or email support.