Skip to content
FluxCDNFluxCDN
esc

Google: Nano Banana Pro (Gemini 3 Pro Image)

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.

Input
720,776 Toman/M tokens
Output
4,324,656 Toman/M tokens
Context
131K
Max output
33K
Published
Jun 18, 2026
Maker
Google

Free plan prices, in Toman at today's rate. Plans and prices

Price by plan

Toman per million tokens at today's rate. A plan lowers the price of your usage up to a limit each period.

PlanInputOutput
Free720,7764,324,656
Pro691,2364,147,416
Max661,6963,970,176

Images and other units

Toman per million tokens of each kind, per plan, at today's rate. A generated 1024×1024 image is usually 1,100–1,300 image tokens on Gemini image models and up to about 6,000 on GPT image models at high quality; the exact count is in each response's usage.

UnitFreeProMax
Generated image tokens43,246,56041,474,16039,701,760

Capabilities

  • Text
  • Vision
  • Tools
  • JSON
  • Reasoning

What it takes and gives

Accepts
  • Text
  • Image
Creates
  • Text
  • Image

Every input listed here works through the API and the playground: images and PDFs as data URLs or https links, audio as base64, video as a data URL or a link the model supports.

This model creates images. The API asks it for images by default (modalities ["image", "text"]); they come back on the message as data URLs. To edit a picture, send it with an instruction.

Call it

Pass google/gemini-3-pro-image as the model name, or let router/auto choose for you.

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://ai.fluxcdn.cloud/api/v1",
    api_key=os.environ["FLUXCDN_API_KEY"],
)

resp = client.chat.completions.create(
    model="router/auto",
    messages=[{"role": "user", "content": "Hello"}],
)

print(resp.choices[0].message.content)