Skip to content
FluxCDNFluxCDN
esc

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration.

Input
92,232 Toman/M tokens
Output
543,144 Toman/M tokens
Context
66K
Max output
59K
Published
Jun 30, 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
Free92,232543,144
Pro88,452520,884
Max84,672498,624

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 tokens10,811,64010,368,5409,925,440

Capabilities

  • Text
  • Vision
  • 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-3.1-flash-lite-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)