Moduck

Google: Nano Banana Pro Preview

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

Model lab
Google
Model family
gemini-pro
Modalitiestext, image → text, image
Context window65,536
Maximum output32,768
InputUSD 0.8 / 1M tokens
OutputUSD 4.8 / 1M tokens

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/google/gemini-3-pro-image-preview.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/google/gemini-3-pro-image-preview"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Nano Banana Pro Preview API Pricing

TypePrice information
InputUSD 0.8 / 1M tokens
OutputUSD 4.8 / 1M tokens
ReasoningUSD 4.8 / 1M tokens
Cached inputUSD 0.08 / 1M tokens
Cache writeUSD 0.15 / 1M tokens

Performance

Performance trends

Image throughput6.3 images/minCurrent
Queue wait0.7 sCurrent
Completion time11.5 sCurrent
Image throughput
Current6.3 images/min
Window average5.9 images/min
Queue wait
Current0.7 s
Window average0.7 s
Completion time
Current11.5 s
Window average12.0 s
Tail completion time (P99)
Current23.6 s
Window average26.0 s
Retry rate
Current0.9%
Window average1.0%
Error rate
Current0.0%
Window average0.1%

Availability

Uptime100%At least one provider responded
Availability100%Requests actually served
Error rate0%Share of failed requests
Served requests, hour by hour
24 hours agoNow

Nano Banana Pro Preview Compare models

ModelInput priceOutput priceContext windowCapabilities
Nano Banana Pro PreviewThis pageUSD 0.8 / 1M tokensUSD 4.8 / 1M tokens65,536Image output · Reasoning
Nano Banana ProUSD 1.6 / 1M tokensUSD 9.6 / 1M tokens65,536Image output · Reasoning
Deep Research Max PreviewUSD 1.6 / 1M tokens · Base context tier (boundary 200000 tokens) · Context ≤ 131072 tokens · Maximum output 65536 tokensUSD 9.6 / 1M tokens · Base context tier (boundary 200000 tokens) · Context ≤ 131072 tokens · Maximum output 65536 tokens1,048,576Image output · Reasoning · Tool calling
Gemini Deep Research PreviewUSD 1.6 / 1M tokens · Base context tier (boundary 200000 tokens) · Context ≤ 131072 tokens · Maximum output 65536 tokensUSD 9.6 / 1M tokens · Base context tier (boundary 200000 tokens) · Context ≤ 131072 tokens · Maximum output 65536 tokens1,048,576Image output · Reasoning · Tool calling
Nano Banana 2 LiteUSD 0.2 / 1M tokensUSD 1.2 / 1M tokens65,536Image output · Reasoning · Tool calling

Model specifications

Input
text, image
Output
text, image
Context window
65,536
Maximum output
32,768
Release date
2025-11-20
Attachments
Yes
Reasoning
Yes
Tool calling
No
Temperature setting
Yes
Open weights
No

Frequently asked questions

What is Nano Banana Pro Preview for?

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

What inputs and outputs does Nano Banana Pro Preview support?

Recorded inputs: text, images; outputs: text, images.

How is Nano Banana Pro Preview priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.8 / 1M tokens; Output USD 4.8 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Nano Banana Pro Preview?

Current model records list Context window 65,536 tokens; Maximum output 32,768 tokens.

What model parameter does the Quickstart use?

The example uses moduck/google/gemini-3-pro-image-preview. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.