Imagen 4 Fast

GoogleImages

Google's Imagen 4 Fast: the quick, low-cost Imagen 4 tier for text-to-image.

Our price
$0.023
per image

First request

from openai import OpenAI

client = OpenAI(
    base_url="https://api.altrouter.ai/v1",
    api_key="ar-...",
)

img = client.images.generate(
    model="imagen-4-fast",
    prompt="a red fox in the snow",
)
print(img.data[0].url)

The interface is OpenAI-compatible: in existing code only the base_url, the key and the model id change — nothing else.

Imagen 4 Fast against its price neighbours

Imagen 4 Fast and its closest neighbours by price: prices and parameters from the AltRouter AI catalog
ModelPriceUnitDiscount
Recraft Crisp UpscaleRecraft$0.0034image−15%Open
Recraft Remove BackgroundRecraft$0.0085image−15%Open
Imagen 4 Fastthis pageGoogle$0.023image
Qwen Image 3.0Alibaba$0.028image−8%Open
Nano Banana 2 LiteGoogle$0.028image−17%Open

Prices and parameters come from the same catalog as the price above; this is not a benchmark, it is comparable billing terms.

Limits

Pricing is flat — $0.023 per image, regardless of prompt length. Allowed aspect_ratio values: 1:1, 16:9, 9:16, 3:4, 4:3.

There is no subscription: every successful request is billed at the price above, and a failed one is not billed at all. There is no markup over the vendor's official price. No Google account of your own is needed, and no VPN: requests go to api.altrouter.ai and we make the upstream call.

Rate limiting is shared across models and counted per key: 600 requests per minute by default, and a 429 with retry-after: 60 above it. An individual key can get its own limit and a spending cap per day, week, month or lifetime in the dashboard.

Full limits and credits

When to pick Imagen 4 Fast, and when a neighbour

The cheaper neighbour is Recraft Remove Background: $0.0085 per image against $0.023 for Imagen 4 Fast. On the same volume the bill comes out 2.7× smaller. It is the sensible pick where the task is repetitive and high-volume — labelling, classification, short templated answers — the kind of work where quality is bounded by the prompt rather than the model.

The dearer neighbour is Qwen Image 3.0: $0.028 per image, or 1.2× the price. On catalog parameters it offers the same capabilities and the same order of context, so the premium is only justified if Imagen 4 Fast falls short on your own task.

Guessing is more expensive than checking: the table above is prices and parameters, not a benchmark, and it cannot tell you which model does better on your own prompt. Switching costs one line — the model id in the request changes, the base_url and the key stay — so running both on your own data takes minutes.

API

OpenAI-compatible image generation endpoint. The result is re-hosted on our CDN and returned as a URL.

POST/v1/images/generations
Body parameters
modelstringrequired"imagen-4-fast"
The model id.
promptstringrequired
The text description of the image.
aspect_ratioenum1:1 · 16:9 · 9:16 · 3:4 · 4:3default 1:1
Output aspect ratio.
negative_promptstring
What to exclude from the image.
seednumber0–2147483647
Seed for reproducibility.
Response
createdinteger
Unix creation time (seconds).
dataarray
Images. Each: url (our CDN), b64_json, revised_prompt.
Example
cURLPythonJavaScriptJSON
curl https://api.altrouter.ai/v1/images/generations \
  -H "Authorization: Bearer ar-..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "imagen-4-fast",
  "prompt": "a red fox in the snow",
  "aspect_ratio": "1:1"
}'
Errors
400Invalid request.
401Missing or invalid API key.
402Insufficient credits, or the key’s spending cap is exhausted.
404Model not found.
429Rate limit exceeded.

More from Google