Nano Banana 2 (Gemini 3.1 Flash Image)

google/gemini-3.1-flash-image

Nano Banana 2 (Gemini 3.1 Flash Image) is Google's image generation and conversational image editing model in the Gemini 3 series, producing images alongside text from text, image, video and PDF input. Google positions it as the high-efficiency, low-latency counterpart to Nano Banana Pro for high-volume developer use, adding output resolutions from 0.5K to 4K, extra wide and tall aspect ratios, image search grounding and improved multilingual text rendering. Choose Nano Banana Pro for complex, precision design work.

Input price
$0.50USD / 1M tokens
Output price
$3.00USD / 1M tokens
Context window
131.1K
Max output
32.8K
Production route

Try the model

Gemini-native API

This model generates images through the Gemini generateContent API and is not available on Chat Completions or in the Playground. Use the request example below with your SandBase API key.

Model card

Specifications

Pricing

Input
$0.50 / 1M tokens
Output
$3 / 1M tokens

Context & modalities

Context window
131,072 tokens
Max output
32,768 tokens
Input
Text, image
Output
Text

Capabilities

Chat
Supported
Vision
Supported
Reasoning
Supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
Google
Model ID
google/gemini-3.1-flash-image
Execution
sync
Base URL
https://api.sandbase.ai
API
Gemini generateContent API
Endpoint
/v1beta/models/google/gemini-3.1-flash-image:generateContent

Start building

Send your first request

Gemini-native endpoint with SandBase API key authentication and usage tracking.

Production API
Gemini generateContent API endpoint
https://api.sandbase.ai/v1beta/models/google/gemini-3.1-flash-image:generateContent
Model ID
google/gemini-3.1-flash-image
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1beta/models/google/gemini-3.1-flash-image:generateContent" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "A watercolor illustration of a fox in a snowy forest"
        }
      ]
    }
  ],
  "generationConfig": {
    "responseModalities": [
      "TEXT",
      "IMAGE"
    ]
  }
}
SANDBASE_JSON
)
printf '%s\n' "$result"

Choose your model

Compare models

All language models
ModelContextInput / 1MOutput / 1MReleased
Google128K$0.50$3.00Jun 18, 2026
Google1M$4.00$20.00Oct 13, 2026
Google64K$1.50$7.50Oct 8, 2026
Google1M$1.50$7.50Sep 2, 2026
Google1M$1.50$7.50Aug 13, 2026
Google1M$0.30$2.50Jul 21, 2026

Questions

FAQ

How do I call Google Nano Banana 2 (Gemini 3.1 Flash Image) through SandBase?

Create a SandBase API key, then send requests with the model ID "google/gemini-3.1-flash-image" to Gemini generateContent API (/v1beta/models/google/gemini-3.1-flash-image:generateContent) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does Google Nano Banana 2 (Gemini 3.1 Flash Image) cost?

$0.50 per 1M input tokens and $3 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

What is the context window of Google Nano Banana 2 (Gemini 3.1 Flash Image)?

131.1K tokens of context, with up to 32.8K output tokens per response.

Which features does Google Nano Banana 2 (Gemini 3.1 Flash Image) support?

Google Nano Banana 2 (Gemini 3.1 Flash Image) supports vision (image input), reasoning. See Specifications above for the full list.

Do I need a separate Google account?

No. One SandBase API key and balance gives you access to Google Nano Banana 2 (Gemini 3.1 Flash Image) and the other models in the catalog; you do not need to sign up with Google separately.