Google: Nano Banana

Nano Banana image model for fast generation, edits, and character-consistent assets

Source-linked gemini-flash Closed weights Released 2025-08-26

API record Report

InputT

OutputT

Input price$0.3/M

Output price$30/M

Context32.768K

Max output32.768K

Providers9

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
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
Kilo Gateway	`google/gemini-2.5-flash-image`	32.768K	8.192K	$0.15	$1.25	$0.015	JSON	Docs ↗
Eden AI	`google/gemini-2.5-flash-image`	32.768K	32.768K	$0.3	$2.5	$0.03	ReasoningJSON	Docs ↗
Merge Gateway	`google/gemini-2.5-flash-image`	32.768K	32.768K	$0.3	$2.5	—	Reasoning	Docs ↗
Google	`gemini-2.5-flash-image`	32.768K	32.768K	$0.3	$30	$0.075	Reasoning	Docs ↗
Eden AI	`vertex/gemini-2.5-flash-image`	32.768K	32.768K	$0.3	$2.5	$0.03	ReasoningJSON	Docs ↗
Vertex	`gemini-2.5-flash-image`	32.768K	32.768K	$0.3	$30	—	Not listed	Docs ↗
Vercel AI Gateway	`google/gemini-2.5-flash-image`	32.768K	65.536K	$0.3	$2.5	$0.03	Not listed	Docs ↗
OpenRouter	`google/gemini-2.5-flash-image`	32.768K	8.192K	$0.3	$2.5	$0.03	JSON	Docs ↗
Abacus	`gemini-2.5-flash-image`	32.768K	32.768K	$0.3	$30	—	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 $0.15/M

Across 9 priced providers

Median input $0.3/M

Midpoint of listed rates

Highest input $0.3/M

2.0× the lowest listed rate

Output range $1.25 – $30

Per million output tokens

Kilo Gateway $0.15/MLowest

Eden AI $0.3/M

Merge Gateway $0.3/M

Google $0.3/M

Eden AI $0.3/M

Vertex $0.3/M

Vercel AI Gateway $0.3/M

OpenRouter $0.3/M

Abacus $0.3/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.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No

× Tool calling No

? Structured output Unknown

✓ Attachments Yes

✓ Vision input Yes

× Open weights No

Creator: Google
Model family: gemini-flash
Knowledge cutoff: 2024-06
License: Not documented
Release date: 2025-08-26
Model ID: google/gemini-2.5-flash-image

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 #4 of 5

1167.0

Design Arena: image elo Source ↗

Design Arena: image #4 of 5

1189.0

Design Arena: logo elo Source ↗

Design Arena: logo #5 of 5

1169.0

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 Tokens8192 → 32768

Sep 11, 2026Price Completion2.5 → 30.0

Sep 11, 2026Max Output Tokens32768 → 8192

Sep 11, 2026Price Completion30.0 → 2.5

Sep 11, 2026Max Output Tokens8192 → 32768

Sep 11, 2026Price Completion2.5 → 30.0

Sep 11, 2026Max Output Tokens32768 → 8192

Sep 11, 2026Price Completion30.0 → 2.5

Sep 11, 2026Max Output Tokens8192 → 32768

Sep 11, 2026Price Completion2.5 → 30.0

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Sep 11, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Models.devcatalog ↗Kilo Gateway documentationprovider documentation ↗Eden AI documentationprovider documentation ↗Merge Gateway documentationprovider documentation ↗Google documentationprovider documentation ↗Vertex documentationprovider documentation ↗Vercel AI Gateway documentationprovider documentation ↗OpenRouter documentationprovider documentation ↗Abacus documentationprovider documentation ↗Design Arena: logoindependent benchmark ↗

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://model.kyssta.lol/api/v1/models/google/gemini-2.5-flash-image

curl

curl "https://model.kyssta.lol/api/v1/models/google/gemini-2.5-flash-image"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Nano Banana?

Nano Banana image model for fast generation, edits, and character-consistent assets. It is published by Google and catalogued here from Models.dev.

How much does Nano Banana cost?

Listed input pricing starts at $0.15 per million tokens from Kilo Gateway, rising to $0.3 across 9 listed providers.

What is the context length of Nano Banana?

Nano Banana accepts up to 32.768K tokens of context and returns up to 32.768K output tokens.

Does Nano Banana support tool calling and structured output?

Provider catalogs list support for image input.

Which providers serve Nano Banana?

8 providers list this model: Kilo Gateway, Eden AI, Merge Gateway, Google, Vertex, Vercel AI Gateway and 2 more.

Are the weights for Nano Banana open?

No. This model is served through hosted APIs only.

When was Nano Banana released?

The catalog records a release date of 2025-08-26, last verified Sep 11, 2026.

More models from Google

View all →

Google: Gemma 3n 4B

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...

32.768K ctx $0.06/M in Google: Gemini 2.5 Pro Preview 06-05

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

1.04858M ctx $1.25/M in Google: Gemma 2 27B

Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...

8.192K ctx $0.65/M in Deep Research Max Preview

Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports

1.04858M ctx