Create an API key

Nano Banana 2.1 API: toman pricing and code

google/gemini-nano-banana-2.1

Image inputTool callingReasoningJSON outputImage output
Create a keyTry it
Input · per 1M tokens
519,329 toman
Output · per 1M tokens
2,596,645 toman
One 1,000-word request ≈
4,051 toman

You are billed for the usage the request actually reported. Prices follow the market. Per generated image: 10.39 toman. Web search: 4,847.07 toman per request.Pricing and top-ups

Nano Banana 2.1 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-nano-banana-2.1",
    "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-nano-banana-2.1",
    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-nano-banana-2.1",
  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 2.1 good for?

Google publishes this model; we expose it under the id "google/gemini-nano-banana-2.1". Its context window is 65,536 tokens, roughly 49k English words in one request. A single response can run to 58,982 tokens. On price it sits in the "mid-range" band — cheaper than 88 and dearer than 308 of the other paid models in the catalogue.

What it can do beyond plain text: it reads images directly, which makes it a real option for invoices, forms and screenshots; it supports tool calling, so it can invoke your own functions with valid arguments; 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.

Pricing is 519,329 toman per 1M input tokens and 2,596,645 per 1M output tokens. A 1,000-word round trip on Nano Banana 2.1 lands near 4,051 toman. Each generated image costs around 10.39 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 Mistral Medium 3.5, and Nano Banana 2.1 costs about the same, 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 25 thousand-word requests on Nano Banana 2.1, and every 1,000 toman is about 247 words of round trip. A job with one million input tokens and one million output tokens comes to 3,115,974 toman in total. Filling this model's 65,536-token window costs 34,035 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "google/gemini-3-pro-image", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out about 38% cheaper (4,051 against 6,301 toman). The context windows differ too: 65,536 against 131,072 tokens. Maximum answer length differs as well: 58,982 against 32,768 tokens. On parameters, this one takes reasoning_effort while the other takes stop.

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. Among the less common parameters it accepts reasoning_effort — all through the standard request body. By context size the nearest option from another provider is LFM2.5-2.6B (free) at 65,536 tokens.

Good fits: product chatbots and internal assistants, where cost and quality have to balance, logic puzzles and code review, pulling text and fields out of images, agents that reach out to APIs and databases, extracting data against a fixed schema.

Provider's own description

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...

Three real jobs, priced on this model

Each figure is derived from the prices above and moves when they do.

JobTokensCost
One chat turn with a medium history1,500 in + 400 out1,818 toman
Summarising a ten-page document4,000 in + 600 out3,635 toman
Classifying a thousand short rows120,000 in + 20,000 out114,252 toman

Frequently asked

How do I call Nano Banana 2.1 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-nano-banana-2.1". Nothing else in your code changes.
What does Nano Banana 2.1 cost in toman?
519,329 toman per 1M input tokens and 2,596,645 toman per 1M output tokens; a 1,000-word request is around 4,051 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Nano Banana 2.1 take?
Up to 65,536 tokens per request, roughly 49k words. A single answer can reach 58,982 tokens.
Does Nano Banana 2.1 support streaming and tool calling?
Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Image input is accepted through image_url, as a data URI or a public URL. Structured output through response_format works too.