Skip to content
ModelCap

Nano Banana 2 (Gemini 3.1 Flash Image)

Image board #2API only

Google·google/gemini-3.1-flash-image

Nano Banana 2 (Gemini 3.1 Flash Image) is a image model published by Google. 2 OpenRouter endpoints are published in the latest snapshot. It accepts image, text input and returns image, text. The published context limit is 131K tokens. The catalogue declares support for reasoning, structured outputs.

Catalogue signals · Image board
23.4#2
Availability and deployment ordering · not a capability score
Market Gravity
35.7
Secondary market signal
Input
—
no comparable token price
Output
—
media-unit price not published
Context
131K
tokens
Providers
2
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
GoogleglobalCheapest——131K—99.87%
Google AI Studio——66K—99.72%

Other versions (2)

Catalogue ordering · Image board

Methodology
23.4
Published availability and deployment signals · not capability
Image board
#2
Public rank basis
Catalogue and deployment signals
Market and catalogue signals · order this category catalogue
Usage (OpenRouter popularity)
12.0
Liquidity (providers × uptime)
69.9
Open reach (HF downloads)
—
Surface (context / tools / modalities)
65.2
Freshness
82.4
  • · OpenRouter popularity #150
  • · 2 live providers
  • · Catalogue: context 131072, reasoning, modalities Image/Text
  • · First seen 2026-06-18

This category board uses only published catalogue and deployment facts. It does not infer media-generation quality or compare incompatible media-unit prices.

This is a discovery ordering, not a capability benchmark. Category-compatible public evaluation evidence must be added before ModelCap can publish a media-quality rank.

Deployment readiness

Metadata index
31.3
limited · 38% metadata coverage
Not capability
Artifact reproducibility
0.0
Access & legal clarity
30.3
Deployability
84.0
Evaluation provenance
0.0

Missing: artifactReproducibility.revision-sha, artifactReproducibility.architecture-and-model-type, artifactReproducibility.parameter-count, artifactReproducibility.serialized-weight-format, artifactReproducibility.base-lineage, accessLegalClarity.declared-license, accessLegalClarity.resolvable-license-terms, evaluationProvenance.admitted-evaluation-observations, evaluationProvenance.capability-family-breadth, evaluationProvenance.evaluation-source-diversity, evaluationProvenance.identity-and-source-confidence, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
35.7
OpenRouter weekly popularity
#150 of 298

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Market Gravity breakdown

Usage55%
12.0

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
69.9

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
82.4

Time since first public availability, on a six-month half-life.

Specification

Context window
131K tokens
Max output
33K tokens
Inputs
Image, Text
Outputs
Image, Text
Tokenizer
Gemini
First seen on OpenRouter
18 Jun 2026

Capabilities

  • Supported: Reasoning
  • Not supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated