Nano Banana Fast
Google's ultra-fast, cheap image generation.
First request
from openai import OpenAI
client = OpenAI(
base_url="https://api.altrouter.ai/v1",
api_key="ar-...",
)
img = client.images.generate(
model="nano-banana-fast",
prompt="a red fox in the snow",
)
print(img.data[0].url)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.altrouter.ai/v1",
apiKey: process.env.ALTROUTER_API_KEY, // ar-...
});
const img = await client.images.generate({
model: "nano-banana-fast",
prompt: "a red fox in the snow",
});
console.log(img.data[0].url);curl https://api.altrouter.ai/v1/images/generations \
-H "Authorization: Bearer ar-..." \
-H "Content-Type: application/json" \
-d '{
"model": "nano-banana-fast",
"prompt": "a red fox in the snow"
}'The interface is OpenAI-compatible: in existing code only the base_url, the key and the model id change — nothing else.
Nano Banana Fast against its price neighbours
| Model | Price | Unit | Discount | |
|---|---|---|---|---|
| FLUX.2 ProBlack Forest | $0.030 | image | — | Open |
| Seedream 5 LiteByteDance | $0.035 | image | — | Open |
| Nano Banana Fastthis pageGoogle | $0.035 | image | −10% | |
| Qwen Image 3.0 ProAlibaba | $0.037 | image | −8% | Open |
| Seedream 4.5ByteDance | $0.040 | image | — | 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 — $0.035 per image, regardless of prompt length. Allowed aspect_ratio values: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9, auto.
There is no subscription: every successful request is billed at the price above, and a failed one is not billed at all. That price is already 10% below the vendor's official one — the official price is shown struck through next to it so it can be checked. No Google account of your own is needed: 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.
When to pick Nano Banana Fast, and when a neighbour
The cheaper neighbour is Seedream 5 Lite: $0.035 per image against $0.035 for Nano Banana Fast. On the same volume the bill comes out 1× 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 Pro: $0.037 per image, or 1× the price. On catalog parameters it offers the same capabilities and the same order of context, so the premium is only justified if Nano Banana 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.
OpenAI-compatible image generation endpoint. The result is re-hosted on our CDN and returned as a URL.
/v1/images/generations