Nano Banana 2 (Gemini 3.1 Flash Image)

Structured outputReasoningImage inputImage outputVideo inputFile input

Launch post Website Docs

Image model for prompt-driven generation, editing, and visual design workflows

Released: 4mo ago
Image output / 1M tokens: From $60

Sources:models.devOpenRouter

Image prices are listed in the billing units published by each provider; resolution and quality can affect the final cost.

Provider pricing

Rates are shown in each provider's published units. Resolution, quality, audio, and other settings may change the final charge.

Google AI Studio

google-ai-studio

Image output

$60.00 / 1,000,000 tokens

Google Vertex

google-vertex/global

Image output

$60.00 / 1,000,000 tokens

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Google DeepMind
Model family: Gemini
Type: Image generation
Predecessor: —
Successor: —
Released: May 28, 2026
Model ID: google/gemini-3.1-flash-image
Openness: Closed
License: —
Input modalities: image, text
Output modalities: image, text
Modality: text+image->text+image
Resolutions: 512, 1K, 2K, 4K
Aspect ratios: 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, 21:9
Images per request: 1
Reference images: 0–14
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: google/gemini-3.1-flash-image
Source family: gemini-flash
Last updated: 2026-05-28
Knowledge cutoff: 2025-01
Model context: 131K
Model output limit: 33K
Open weights: No
File attachments: Yes
Reasoning: Yes
Tool calling: No
Temperature control: Yes

Complete source record (JSON)

{
  "id": "google/gemini-3.1-flash-image",
  "name": "Nano Banana 2",
  "description": "Image model for prompt-driven generation, editing, and visual design workflows",
  "family": "gemini-flash",
  "last_updated": "2026-05-28",
  "knowledge": "2025-01",
  "attachment": true,
  "reasoning": true,
  "tool_call": false,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "video",
      "pdf"
    ],
    "output": [
      "text",
      "image"
    ]
  },
  "limit": {
    "context": 131072,
    "output": 32768
  },
  "release_date": "2026-05-28",
  "open_weights": false
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Pricing (published units)	Uptime 1d	Data handling
Google	google-vertex/global	$60 (Image output / 1M tokens)	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Google AI Studio	google-ai-studio	$60 (Image output / 1M tokens)	96.48%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Text provenance

Gemini app/web

Google SynthID text watermarking

Google DeepMind says text generated in the Gemini app and web experience is watermarked with SynthID by adjusting token probabilities.

Official explanation