Google logo

Google: Nano Banana Pro Preview

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

Source-linked gemini-pro Closed weights Released 2025-11-20
API record Report
InputT
OutputT
Input price$1/M
Output price$6/M
Context65.536K
Max output32.768K
Providers11
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 Pro Preview
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Kilo Gateway google/gemini-3-pro-image-preview 65.536K 32.768K $1 $6 $0.1 ReasoningJSON Docs ↗
Eden AI google/gemini-3-pro-image-preview 65.536K 32.768K $2 $12 $0.2 ReasoningJSON Docs ↗
Vertex gemini-3-pro-image 65.536K 32.768K $2 $120 $0.2 Reasoning Docs ↗
Requesty gemini-3-pro-image 1.04858M 32.768K $2 $12 $0.2 ReasoningToolsJSON Docs ↗
FastRouter google/gemini-3-pro-image-preview 65.536K 32.768K $2 $12 Reasoning Docs ↗
Google gemini-3-pro-image 131.072K 32.768K $2 $120 Reasoning Docs ↗
OpenRouter google/gemini-3-pro-image-preview 65.536K 32.768K $2 $12 $0.2 ReasoningJSON Docs ↗
Abacus gemini-3-pro-image 65.536K 32.768K $2 $12 $0.2 Reasoning Docs ↗
Abacus gemini-3-pro-image-preview 65.536K 32.768K $2 $12 $0.2 Reasoning Docs ↗
Eden AI vertex/gemini-3-pro-image 65.536K 32.768K $2 $12 $0.2 ReasoningJSON Docs ↗
Google gemini-3-pro-image-preview 131.072K 32.768K $2 $120 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 $1/M

Across 11 priced providers

Median input $2/M

Midpoint of listed rates

Highest input $2/M

2.0× the lowest listed rate

Output range $6 – $120

Per million output tokens

Kilo Gateway $1/MLowest
Eden AI $2/M
Vertex $2/M
Requesty $2/M
FastRouter $2/M
Google $2/M
OpenRouter $2/M
Abacus $2/M
Abacus $2/M
Eden AI $2/M
Google $2/M
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

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-pro
Knowledge cutoff
2025-01
License
Not documented
Release date
2025-11-20
Model ID
google/gemini-3-pro-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
Design Arena: g…Design Arena: graphicdesign Design Arena: i…Design Arena: image Design Arena: l…Design Arena: logo This model — Design Arena: graphicdesign: 1250 elo (70.0th percentile) This model — Design Arena: image: 1246 elo (70.0th percentile) This model — Design Arena: logo: 1240 elo (70.0th percentile)

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 #2 of 5
Design Arena: image elo Source ↗
Design Arena: image #2 of 5
Design Arena: logo elo Source ↗
Design Arena: logo #2 of 5
Design Arena: imageediting elo Source ↗
1254.0 1 model scored — too few for a distribution

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
Price Completion12.0 → 6.0
Price Prompt2.0 → 1.0
Price Completion6.0 → 12.0
Price Prompt1.0 → 2.0
Price Completion12.0 → 6.0
Price Prompt2.0 → 1.0
Price Completion6.0 → 12.0
Price Prompt1.0 → 2.0
Price Completion12.0 → 6.0
Price Prompt2.0 → 1.0
Provenance

Sources & verification

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

Methodology
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-3-pro-image-preview
curl
curl "https://model.kyssta.lol/api/v1/models/google/gemini-3-pro-image-preview"
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 Pro Preview?

Nano Banana Pro for higher-fidelity image generation and design-heavy edits. It is published by Google and catalogued here from Models.dev.

How much does Nano Banana Pro Preview cost?

Listed input pricing starts at $1 per million tokens from Kilo Gateway, rising to $2 across 11 listed providers.

What is the context length of Nano Banana Pro Preview?

Nano Banana Pro Preview accepts up to 65.536K tokens of context and returns up to 32.768K output tokens.

Does Nano Banana Pro Preview support tool calling and structured output?

Provider catalogs list support for reasoning, and image input.

Which providers serve Nano Banana Pro Preview?

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

Are the weights for Nano Banana Pro Preview open?

No. This model is served through hosted APIs only.

When was Nano Banana Pro Preview released?

The catalog records a release date of 2025-11-20, last verified Sep 11, 2026.

More models from Google

View all →