modelgrep
G

Google: Nano Banana (Gemini 2.5 Flash Image)

google/gemini-2.5-flash-image

JSONVisionImage out
Use via OpenRouter ↗
Intelligence
Design Elo
1213
image
Speed
224
14th fastest
Latency
894ms
first token
Input price
$0.300
134th cheapest
Context
33K
33K max out

How it compares

Faster than95%
of all ranked models
Cheaper than55%
of all ranked models

Overview

Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...

Benchmarks

independent · via OpenRouter
Design Arena · Elo33,135 tournaments
image
1213
logo
1188
graphicdesign
1184

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Google AI Studio$0.300$2.50100%
Google$0.300$2.5099.9%

Specifications

Context window33K
Max output33K
Knowledge cutoffJan 2025
Input modalitiesimage, text
Output modalitiesimage, text
Prompt caching
Cache read price$0.030/M
ModeratedNo

Nano Banana (Gemini 2.5 Flash Image) FAQ

How much does Nano Banana (Gemini 2.5 Flash Image) cost?

Nano Banana (Gemini 2.5 Flash Image) costs $0.300 per million input tokens and $2.50 per million output tokens via OpenRouter, making it 134th cheapest of 298 paid models.

How fast is Nano Banana (Gemini 2.5 Flash Image)?

Nano Banana (Gemini 2.5 Flash Image) generates around 224 tokens per second with 894ms time-to-first-token (p50), the 14th fastest tracked model.

What is Nano Banana (Gemini 2.5 Flash Image)'s context window?

Nano Banana (Gemini 2.5 Flash Image) supports a 33K-token context window and can output up to 33K tokens. It accepts image, text input.

Compare head-to-head