Speed-first design
It generates in roughly 2.7 seconds per image, up to 10 times faster than Imagen 3, which makes quick iteration practical.
Image by Google
Imagen 4 Fast API
Google DeepMind's speed-optimized tier in the Imagen 4 family (May 2025), built for rapid, high-volume, and interactive image generation at the lowest cost in the lineup.
Integrate Imagen 4 Fast with a single API call — one key, one unified endpoint, and shared billing across every model on Apiframe.
model: "imagen-4-fast" 
What's special about Imagen 4 Fast
The lowest cost in the family
At 4 credits ($0.04) per image, it suits high-volume tasks like large prompt sets and product-catalog generation.
Built for real-time experiences
Its low latency makes interactive features viable, such as live-preview creative tools, product configurators, and social features.
Same workflow as the rest of the family
It shares the Imagen 4 endpoint and prompt structure, so you can prototype on Fast and swap to Standard or Ultra when you need more detail.
Keeps Imagen 4's core strengths
It retains the family's improved text rendering and style versatility, trading only the finest detail for speed.
Built-in watermarking and controls
Outputs carry Google's invisible SynthID watermark, with configurable safety settings and an optional prompt rewriter.
Made with Imagen 4 Fast
A few outputs generated through the Imagen 4 Fast API on Apiframe.
A quick concept sketch of a futuristic sneaker in three color variations, clean studio background.
A social media graphic reading 'WEEKEND SALE' with bright bold type.
A simple flat-style icon set of weather symbols: sun, cloud, rain, and snow.
A landscape thumbnail of a desert highway at sunset, warm tones.
A set of mascot poses for a coffee brand, friendly cartoon bean character.
A blog header of a tidy home office with a laptop and a plant, soft daylight.
Overview
- Endpoint
- POST /v2/images/generate
- Model ID
- imagen-4-fast
- Params key
- imagenParams
- Modality
- Image
- Provider
- Avg. completion
- ~8s
Capabilities
Aspect ratios1:1, 9:16, 16:9, 3:4, 4:3
Avg. time~8s
Quick start
Send a single POST /v2/images/generate request with your API key to
generate with Imagen 4 Fast. The call returns a jobId you can poll or
receive via webhook.
curl -X POST https://api.apiframe.ai/v2/images/generate \
-H "X-API-Key: afk_your_api_key_here" \
-H "Content-Type: application/json" \
-d '{
"prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
"model": "imagen-4-fast",
"imagenParams": {
"image_size": "1K",
"output_format": "jpg"
}
}'import requests
response = requests.post(
"https://api.apiframe.ai/v2/images/generate",
headers={
"X-API-Key": "afk_your_api_key_here",
"Content-Type": "application/json",
},
json={
"prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
"model": "imagen-4-fast",
"imagenParams": {
"image_size": "1K",
"output_format": "jpg"
}
},
)
print(response.json()) # { "jobId": "...", "status": "QUEUED" }const response = await fetch("https://api.apiframe.ai/v2/images/generate", {
method: "POST",
headers: {
"X-API-Key": "afk_your_api_key_here",
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
"model": "imagen-4-fast",
"imagenParams": {
"image_size": "1K",
"output_format": "jpg"
}
}),
});
const { jobId } = await response.json();
console.log(jobId);Response & job lifecycle
Generation is asynchronous. A successful submission returns 202 Accepted with a jobId. Poll GET /v2/jobs/{id} (or supply a webhook_url) until the status is COMPLETED; the result field then holds the output URL(s).
1. Submission response (202)
{
"jobId": "b2c3d4e5-f6a7-8901-bcde-f23456789012",
"status": "QUEUED"
}2. Poll for the result
curl https://api.apiframe.ai/v2/jobs/JOB_ID \
-H "X-API-Key: afk_your_api_key_here"import requests, time
while True:
job = requests.get(
"https://api.apiframe.ai/v2/jobs/JOB_ID",
headers={"X-API-Key": "afk_your_api_key_here"},
).json()
if job["status"] in ("COMPLETED", "FAILED"):
break
time.sleep(2)
print(job["result"])let job;
do {
await new Promise((r) => setTimeout(r, 2000));
job = await fetch("https://api.apiframe.ai/v2/jobs/JOB_ID", {
headers: { "X-API-Key": "afk_your_api_key_here" },
}).then((r) => r.json());
} while (job.status !== "COMPLETED" && job.status !== "FAILED");
console.log(job.result);Input schema
Request parameters accepted by the Imagen 4 Fast endpoint. Model-specific options are nested under the params object shown below.
| Parameter | Type | Required | Default | Allowed / range | Description |
|---|---|---|---|---|---|
| prompt | string | required | — | — | Text description of what to generate. |
| model | string | required | "imagen-4-fast" | "imagen-4-fast" | The model identifier for this endpoint. |
| imagenParams.image_size | string | optional | "1K" | "1K", "2K" | Resolution |
| imagenParams.output_format | string | optional | "jpg" | "jpg", "png" | Output format |
Frequently Asked Questions
Common questions about the Imagen 4 Fast API.
What is Imagen 4 Fast?
The speed-optimized tier of Google's Imagen 4 family, released in May 2025 for rapid, high-volume generation.
How fast and how cheap is it?
About 2.7 seconds per image at 4 credits ($0.04) each, up to 10 times faster than Imagen 3.
What resolution does it produce?
Up to 1408x768, lower than the 2K output of Standard and Ultra.
What is it best for?
Rapid prototyping, high-volume and batch jobs, and interactive features that need near-real-time results.
How is it different from Standard and Ultra?
It prioritizes speed and cost over maximum detail, while sharing the same endpoint and prompt structure.
Where can you access it?
Through Apiframe, as well as the Gemini API, Google AI Studio, and Vertex AI.
Still have questions?
Start building with the Imagen 4 Fast API
Get your API key and integrate Imagen 4 Fast in minutes — Pay-as-you-go.
Free credits to start
One API for every model
Webhooks, SDKs & idempotency
No provider account required
Questions? Join our Discord or contact sales.