Nano Banana Pro (Gemini 3 Pro Image Preview) API: toman pricing and code
google/gemini-3-pro-image-preview
You are billed for the usage the request actually reported. Prices follow the market. Cached input: 69,244 toman per 1M tokens. Reasoning tokens: 4,154,632 toman per 1M tokens. Per input image: 0.69 toman. Per generated image: 41.55 toman. Web search: 4,847.07 toman per request.Pricing and top-ups
Nano Banana Pro (Gemini 3 Pro Image Preview) example: image generation
The example is picked from this model's own capabilities. Drop in your key and it runs as is.
curl https://api.uttapen.ir/v1/chat/completions \
-H "Authorization: Bearer sk-up-…" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-3-pro-image-preview",
"messages": [{"role": "user", "content": "A minimal photo of a coffee cup on a wooden table, natural light"}],
"modalities": ["image", "text"]
}'import base64
from openai import OpenAI
client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")
resp = client.chat.completions.create(
model="google/gemini-3-pro-image-preview",
messages=[{"role": "user", "content": "A minimal photo of a coffee cup on a wooden table, natural light"}],
extra_body={"modalities": ["image", "text"]},
)
# images are billed on image output tokens — check the balance before generating in bulk
for img in resp.choices[0].message.images or []:
data = img["image_url"]["url"].split(",", 1)[1]
open("out.png", "wb").write(base64.b64decode(data))
print("saved out.png")import OpenAI from "openai";
import { writeFileSync } from "node:fs";
const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });
const resp = await client.chat.completions.create({
model: "google/gemini-3-pro-image-preview",
messages: [{ role: "user", content: "A minimal photo of a coffee cup on a wooden table, natural light" }],
modalities: ["image", "text"],
});
for (const img of resp.choices[0].message.images ?? []) {
const b64 = img.image_url.url.split(",", 2)[1];
writeFileSync("out.png", Buffer.from(b64, "base64"));
}What is Nano Banana Pro (Gemini 3 Pro Image Preview) good for?
Google publishes this model; we expose it under the id "google/
What you get on top of text in, text out: it reads images directly, which makes it a real option for invoices, forms and screenshots; it returns schema-valid JSON through response_format, ready to hand to your code; it has a reasoning mode that pays off on multi-step problems, maths and debugging; it can return generated images. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper. Keep in mind that reasoning tokens are output tokens and do appear on the bill.
Input runs at 692,439 toman per 1M tokens and output at 4,154,632 — output costs 6× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 69,244 toman per 1M, which matters a lot if your system prompt is long. Each input image is billed separately at about 0.69 toman. Each generated image costs around 41.55 toman. You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.
The closest alternative with the same capabilities from a different provider is GPT-5 Image: Nano Banana Pro (Gemini 3 Pro Image Preview) works out about 29% cheaper, and its context window is smaller. Both run on the same key and the same code, so trying the other one is a single string change.
To make the figure concrete: 100,000 toman of credit buys roughly 16 thousand-word requests on Nano Banana Pro (Gemini 3 Pro Image Preview), and every 1,000 toman is about 159 words of round trip. A job with one million input tokens and one million output tokens comes to 4,847,071 toman in total. Filling this model's 65,536-token window costs 45,380 toman on the input side alone, which is the real reason to keep conversation history short.
Its nearest relative in the catalogue is "google/
Google has 43 models in our catalogue; the cheapest is Gemma 4 26B A4B at 67 toman per thousand words and the dearest Gemini 3.1 Pro Preview Custom Tools at 6,301. It does not support tool_choice, tools, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is LFM2.5-2.6B (free) at 65,536 tokens.
Where it makes sense: work where the quality of the answer matters more than its cost, logic puzzles and code review, pulling text and fields out of images, extracting data against a fixed schema.
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
Three real jobs, priced on this model
Each figure is derived from the prices above and moves when they do.
| Job | Tokens | Cost |
|---|---|---|
| One chat turn with a medium history | 1,500 in + 400 out | 2,701 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 5,263 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 166,185 toman |
Frequently asked
- How do I call Nano Banana Pro (Gemini 3 Pro Image Preview) from Iran?
- Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https:/
/ api.uttapen.ir/ v1 and set model to "google/ gemini-3-pro-image-preview". Nothing else in your code changes. - What does Nano Banana Pro (Gemini 3 Pro Image Preview) cost in toman?
- 692,439 toman per 1M input tokens and 4,154,632 toman per 1M output tokens; a 1,000-word request is around 6,301 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does Nano Banana Pro (Gemini 3 Pro Image Preview) take?
- Up to 65,536 tokens per request, roughly 49k words. A single answer can reach 32,768 tokens.
- Does Nano Banana Pro (Gemini 3 Pro Image Preview) support streaming and image input?
- Streaming (stream=true) works on every model here. Image input is accepted through image_url, as a data URI or a public URL. Structured output through response_format works too.