Nano Banana is Google’s name for its Gemini image models. Nano Banana Pro is Gemini 3 Pro Image, the high-fidelity model. Nano Banana 2 is Gemini 3.1 Flash Image, the fast one. Google bills both per image, and the price climbs with resolution. This page puts Google’s list prices next to what APIMODELS charges, tier by tier. It also explains why the same Google model appears here under more than one model id, because that choice changes both the price and how often a prompt gets refused.
Google’s list prices, verified on 2026-09-26 and unchanged since July: Gemini 3 Pro Image is $0.134 per image at 1K or 2K and $0.24 at 4K. Gemini 3.1 Flash Image is $0.045 at 512px, $0.067 at 1K, $0.101 at 2K and $0.151 at 4K. Google also sells a queued batch tier whose jobs can take up to a day; every request here is real time.
For Nano Banana Pro there are three ids. gemini-3-pro-image is Google’s GA release: $0.08 at 1K or 2K and $0.13 at 4K, and over the last 30 days it refused only 3.6% of prompts on content grounds. gemini-3-pro-image-preview is slightly lower at 1K or 2K ($0.068) and the same $0.13 at 4K, but runs on a different channel whose content filter is stricter: 12.5% of prompts were refused over the same period. Google retired the preview id on its own API on 2026-06-25; we keep it working for existing integrations. gemini-3-pro-image-gemini is a budget channel at a flat $0.03 per image at any resolution, but it is slow, with a median of about 93 seconds.
For Nano Banana 2 the choice is similar. gemini-3.1-flash-image is the GA release: $0.04 at 512px, $0.06 at 1K or 2K and $0.10 at 4K. Because 1K and 2K cost the same, 2K is effectively a free upgrade, and it is 41% below Google’s $0.101. gemini-3.1-flash-image-preview is $0.05 at 1K or 2K and $0.08 at 4K, again on a stricter channel.
A simple rule: use the GA ids by default. Pick a preview id only if you are cost-sensitive and your prompts rarely touch people, brands or anything else a content filter might flag. Use the $0.03 channel only for batch-style jobs that can wait.
Over the last 30 days of external production traffic (internal accounts excluded). Success rate counts every request, including prompts refused by the content filter, which are listed separately. Failed requests are never billed.
| Model id | Calls | Success | Refused by filter | Median | p95 |
|---|---|---|---|---|---|
| gemini-3-pro-image | 504 | 96.0% | 3.6% | 40.4 s | 154.4 s |
| gemini-3-pro-image-preview | 23,194 | 87.3% | 12.5% | 33.5 s | 88.1 s |
| gemini-3-pro-image-gemini | 2,114 | 89.2% | 3.9% | 92.8 s | 241.7 s |
| gemini-3.1-flash-image | 2,828 | 98.6% | 1.3% | 32.1 s | 70.2 s |
| gemini-3.1-flash-image-preview | 1,317 | 87.9% | 10.5% | 32.7 s | 95.0 s |
Gemini 2.5 Flash Image is $0.02 per image here against Google’s $0.039. Google has announced that it will shut the model down on 2026-10-02, so we do not recommend building anything new on it. Nano Banana 2 at $0.06 for 1K or 2K is the natural replacement.
Price per image — Google list vs APIMODELS, verified 2026-09-26
512px 1K 2K 4K
Nano Banana Pro (Gemini 3 Pro Image)
Google (list) -- $0.134 $0.134 $0.24
gemini-3-pro-image -- $0.08 $0.08 $0.13 -40% / -46%
gemini-3-pro-image-preview -- $0.068 $0.068 $0.13 -49% / -46%
gemini-3-pro-image-gemini -- $0.03 $0.03 $0.03 slow channel
Nano Banana 2 (Gemini 3.1 Flash Image)
Google (list) $0.045 $0.067 $0.101 $0.151
gemini-3.1-flash-image $0.04 $0.06 $0.06 $0.10 2K -41%
gemini-3.1-flash-image-preview -- $0.05 $0.05 $0.08 2K -50%
Per image, real time. Failed requests are not billed.
Reference (input) images are not charged separately.cURL
# Step 1: create the task
curl -X POST https://api.apimodels.app/v1/images/generations \
-H "Authorization: Bearer $APIMODELS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3-pro-image",
"prompt": "A product photo of a ceramic mug on a linen tablecloth, soft window light",
"aspect_ratio": "16:9",
"resolution": "2k"
}'
# Step 2: poll until state is completed
curl "https://api.apimodels.app/v1/images/generations?task_id=TASK_ID" \
-H "Authorization: Bearer $APIMODELS_API_KEY"Python
import requests, time
H = {"Authorization": "Bearer YOUR_APIMODELS_KEY"}
URL = "https://api.apimodels.app/v1/images/generations"
task = requests.post(URL, headers=H, json={
"model": "gemini-3.1-flash-image", # 2K costs the same as 1K here
"prompt": "Isometric illustration of a tiny coffee shop, pastel colors",
"aspect_ratio": "16:9",
"resolution": "2k",
}).json()["data"]["taskId"]
while True:
r = requests.get(URL, headers=H, params={"task_id": task}).json()["data"]
if r["state"] in ("completed", "failed"):
break
time.sleep(3)
print(r)Google lists Nano Banana Pro (Gemini 3 Pro Image) at $0.134 per image at 1K or 2K and $0.24 at 4K, and Nano Banana 2 (Gemini 3.1 Flash Image) at $0.067, $0.101 and $0.151 for 1K, 2K and 4K. On APIMODELS, gemini-3-pro-image is $0.08 / $0.08 / $0.13 and gemini-3.1-flash-image is $0.06 / $0.06 / $0.10, with a lower 1K/2K price on the preview id and a budget option described above.
Same Google model family, different channels. The GA id costs $0.08 at 1K or 2K and, over the last 30 days, refused 3.6% of prompts on content grounds. The preview id costs $0.068 but runs on a channel with a stricter filter that refused 12.5%. Refused requests are not billed, but they cost you a retry. Use GA by default and the preview id when price matters more than the occasional refusal.
That is simply how the tier is priced here. Google charges $0.067 for 1K and $0.101 for 2K; here both are $0.06, which makes 2K 41% below Google’s list. If you were rendering at 1K to save money, you can render at 2K for the same price.
It is a different product. Batch jobs are queued and can take up to 24 hours to come back, so it only suits offline work that can wait. For anything interactive or user-facing, the real-time prices on this page are the relevant comparison.
Google has announced that it will shut Gemini 2.5 Flash Image down on 2026-10-02. It is $0.02 per image here until then, but do not start new work on it. Gemini 3.1 Flash Image is the replacement: better quality, and $0.06 for 1K or 2K.
No. Sign up at apimodels.app, create an API key and call https://api.apimodels.app/v1/images/generations. There is no Google Cloud project, billing setup or region selection, it works from mainland China, and the same key and USD balance cover every other image, video and language model on the platform.
