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
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.
| Plan | Input | Output |
|---|---|---|
| Free | 720,776 | 4,324,656 |
| Pro | 691,236 | 4,147,416 |
| Max | 661,696 | 3,970,176 |
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.
| Unit | Free | Pro | Max |
|---|---|---|---|
| Generated image tokens | 43,246,560 | 41,474,160 | 39,701,760 |
Capabilities
- Text
- Vision
- Tools
- JSON
- Reasoning
What it takes and gives
- Text
- Image
- 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)
