Nano Banana 2

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced contextual understanding with fast, cost-efficient inference, making complex image generation and iterative edits significantly more accessible. Aspect ratios can be controlled with the image_config API Parameter

google/gemini-3.1-flash-image

Organization: Google
Family: gemini-flash
Providers: 10
Context: 131,072
Output limit: 32,768
Knowledge: 2025-01
Release: 2026-05-28
Updated: 2026-05-28
Weights: Closed
Input: text, image, video, pdf
Output: text, image
Capabilities: Reasoning, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

12 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Abacus	gemini-3.1-flash-image	1,048,576	32,768	$0.50 / $3.00	Yes	No	—	View
AIHubMix	gemini-3.1-flash-image	131,072	32,768	$0.50 / $3.00	Yes	No	—	View
Eden AI	vertex/gemini-3.1-flash-image	131,072	32,768	$0.50 / $3.00	Yes	No	Yes	View
Eden AI	google/gemini-3.1-flash-image	65,536	32,768	$0.50 / $3.00	Yes	No	Yes	View
Google	gemini-3.1-flash-image	131,072	32,768	$0.50 / $60.00	Yes	No	—	View
Kilo Gateway	google/gemini-3.1-flash-image	131,072	32,768	$0.50 / $3.00	Yes	No	Yes	View
Merge Gateway	google/gemini-3.1-flash-image	32,768	32,768	$0.50 / $3.00	Yes	No	No	View
Googlevia OpenRouter	google/gemini-3.1-flash-image unknown	131,072	32,768	$0.50 / $3.00	Yes	No	No	View
Google AI Studiovia OpenRouter	google/gemini-3.1-flash-image unknown	65,536	58,982	$0.50 / $3.00	Yes	No	Yes	View
Requesty	gemini-3.1-flash-image	131,072	32,768	$0.50 / $2.00	Yes	Yes	No	View
Vercel AI Gateway	google/gemini-3.1-flash-image	131,072	32,768	$0.50 / $3.00	Yes	No	—	View
Vertex	gemini-3.1-flash-image	131,072	32,768	$0.50 / $60.00	Yes	No	—	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.50Per 1M input tokens

Output from$2.00Per 1M output tokens

Available offers12Across 10 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 2 lowest-priced configurations

InputOutput

Googlegoogle-vertex/global

$0.50$3.00

Google AI Studiogoogle-ai-studio

$0.50$3.00

google/gemini-3.1-flash-imageObserved Oct 4, 2026, 11:31 AM UTC

Input: $0.50
Output: $3.00

Additional fees and pricing conditions

web search: $0.014 / search
image output: $0.00006 / image

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Googlegoogle-vertex/global	$0.50	$3.00	—	—
Google AI Studiogoogle-ai-studio	$0.50	$3.00	—	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 2 endpoints

P50P75P90P99

Googlegoogle-vertex/global

17,874.5–32,351.04 ms

Google AI Studiogoogle-ai-studio

18,685–52,711.1 ms

All latency percentiles 2 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/global	17,874.5 ms	19,855.5 ms	22,514.1 ms	32,351.04 ms
Google AI Studiogoogle-ai-studio	18,685 ms	37,961.5 ms	44,107 ms	52,711.1 ms

Output throughput · tokens per second

All throughput percentiles 2 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/global	0 t/s	0 t/s	0 t/s	0 t/s
Google AI Studiogoogle-ai-studio	0 t/s	0 t/s	0 t/s	0 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 2 endpoints

Endpoint5 minutes30 minutes24 hours

Googlegoogle-vertex/globalObserved Oct 4, 2026, 11:31 AM UTC

100%

99.94%

99.96%

Google AI Studiogoogle-ai-studioObserved Oct 4, 2026, 11:31 AM UTC

—

99.9%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

google/gemini-3.1-flash-imageObserved Oct 4, 2026, 11:31 AM UTC

Context: 131,072
Maximum output: 32,768
Tokenizer: Gemini
Input: image, text
Output: image, text
Moderation: No
Added to OpenRouter: 2026-06-18

Base URLhttps://openrouter.ai/api/v1

Model IDgoogle/gemini-3.1-flash-image

Version IDgoogle/gemini-3.1-flash-image-20260528

Reasoning

Required: No
Enabled by default: Yes
Default effort: minimal
Supported efforts: high, minimal

Supported parameters

include_reasoning
max_tokens
reasoning
reasoning_effort
response_format
seed
structured_outputs
temperature
top_p

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Nano Banana 2 cost?

Listed rates start at $0.50 per million input tokens and $2.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Nano Banana 2?

There are 12 cataloged offers across 10 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 131,072 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: No. Structured output: Not reported. Support can vary by endpoint.

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · c1c64b0a53ae
Sep 12, 2026 · 38e39fa7978e