Google: Nano Banana 2 Preview

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

Source-linked gemini-flash Closed weights Released 2026-02-26

API record Report

InputT

OutputT

Input price$0.5/M

Output price$3/M

Context65.536K

Max output65.536K

Providers12

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering Nano Banana 2 Preview
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
Google	`gemini-3.1-flash-image`	65.536K	65.536K	$0.5	$60	—	Reasoning	Docs ↗
Eden AI	`vertex/gemini-3.1-flash-image`	131.072K	32.768K	$0.5	$3	—	ReasoningJSON	Docs ↗
Google	`gemini-3.1-flash-image-preview`	65.536K	65.536K	$0.5	$60	—	Reasoning	Docs ↗
Eden AI	`google/gemini-3.1-flash-image-preview`	65.536K	65.536K	$0.5	$3	—	ReasoningJSON	Docs ↗
Abacus	`gemini-3.1-flash-image`	1.04858M	32.768K	$0.5	$3	—	Reasoning	Docs ↗
Requesty	`gemini-3.1-flash-image`	131.072K	32.768K	$0.5	$2	—	ReasoningTools	Docs ↗
FastRouter	`google/gemini-3.1-flash-image-preview`	65.536K	65.536K	$0.5	$3	—	Reasoning	Docs ↗
Vercel AI Gateway	`google/gemini-3.1-flash-image-preview`	131.072K	32.768K	$0.5	$3	$0.05	Reasoning	Docs ↗
OpenRouter	`google/gemini-3.1-flash-image-preview`	65.536K	58.982K	$0.5	$3	—	ReasoningJSON	Docs ↗
Abacus	`gemini-3.1-flash-image-preview`	1.04858M	32.768K	$0.5	$3	—	Reasoning	Docs ↗
Kilo Gateway	`google/gemini-3.1-flash-image-preview`	65.536K	58.982K	$0.5	$3	—	ReasoningJSON	Docs ↗
Vertex	`gemini-3.1-flash-image`	131.072K	32.768K	$0.5	$60	$0.05	Reasoning	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.5/M

Across 12 priced providers

Median input $0.5/M

Midpoint of listed rates

Highest input $0.5/M

Same as the lowest listed rate

Output range $2 – $60

Per million output tokens

Google $0.5/M

Eden AI $0.5/M

Google $0.5/M

Eden AI $0.5/M

Abacus $0.5/M

Requesty $0.5/M

FastRouter $0.5/M

Vercel AI Gateway $0.5/M

OpenRouter $0.5/M

Abacus $0.5/M

Kilo Gateway $0.5/M

Vertex $0.5/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

12 providers list the identical $0.5 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.

Context limits also differ by provider, from 65.536K to 1.04858M tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes

× Tool calling No

? Structured output Unknown

✓ Attachments Yes

✓ Vision input Yes

× Open weights No

Creator: Google
Model family: gemini-flash
Knowledge cutoff: 2025-01
License: Not documented
Release date: 2026-02-26
Model ID: google/gemini-3.1-flash-image-preview

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

Benchmark profile

Each axis is this model's percentile among the 3 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.

Design Arena: graphicdesign elo Source ↗

Design Arena: graphicdesign #1 of 5

1261.0

Design Arena: image elo Source ↗

Design Arena: image #1 of 5

1279.0

Design Arena: logo elo Source ↗

Design Arena: logo #1 of 5

1262.0

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

Sep 11, 2026Max Output Tokens58982 → 65536