Nano Banana 2 (Gemini 3.1 Flash Image Preview)

Chat Completions

gemini-3.1-flash-image-preview

Google|Created Feb 27, 2026|128k context

Chat Completions

Nano Banana 2 (Gemini 3.1 Flash Image) is Google DeepMind’s flagship Flash image model for high-fidelity generation and fast, advanced editing at scale, optimized for price–performance. It follows complex prompts more reliably and adds configurable thinking levels (Minimal vs High/Dynamic) to balance latency and quality. Nano Banana 2 improves in-image text rendering and supports in-image localization (generate/translate text across languages directly in the image), while leveraging stronger world knowledge and web image search for more grounded, realistic outputs. It supports native aspect ratios (including 4:1, 1:4, 8:1, 1:8) and 512px/1K/2K/4K resolutions.

Overview Specifications Activity Performance Uptime Examples

Pricing-50%

Pay-as-you-go rates for this model. More details can be found here.

Input Tokens (1M)

$0.13

Output Tokens (1M)

$0.75

Capabilities

Input Modalities

TextImageAudioFile

Output Modalities

TextImage

Supported Parameters

Available parameters for API requests

Max Completion TokensReasoning EffortResponse FormatStopTemperatureTool ChoiceToolsTop PWeb Search OptionsImage Config

Usage Analytics

Token usage of this model on our platform

Throughput

Time-To-First-Token (TTFT)

Code Example

Example code for using this model through our API with Python (OpenAI SDK) or cURL. Replace placeholders with your API key and model ID.

Basic request example. Ensure API key permissions. For more details, see our documentation.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.naga.ac/v1",
    api_key="YOUR_API_KEY",
)

resp = client.chat.completions.create(
    model="gemini-3.1-flash-image-preview",
    messages=[
        {"role": "user", "content": "What's 2+2?"}
    ],
    temperature=0.2,
)
print(resp.choices[0].message.content)