Nano Banana 2
GoogleReleased May 28, 2026
- providers
- 1
- context
- 65.5K
- max out
- 65.5K
- input /M
- $0.50
- output /M
- $60.00
- cached input /M
- $0.50
- cache write /M
- $0.50
- reasoning /M
- $60.00
About
Drafted from the provider's own page.
Nano Banana 2 provides high-quality image generation and conversational editing at a mainstream price point and low latency. It serves as the high-efficiency counterpart to Gemini 3 Pro Image , optimized for speed and high-volume developer use cases.
- knowledge cutoff
- Jan 1, 2025
- open weights
- no
- best for
- extractioncoding
Capabilities
What the model accepts and returns, where a probe through our own gateway proved it.
- streaming
- tools
- json mode
- vision
- audio
Providers
What you pay through us for each provider, and its own list price where that differs.
Google
google-aistudio/gemini-3.1-flash-image- input /M
- $0.50
- output /M
- $60.00
- cache read /M
- $0.50
- cache write /M
- $0.50
Cache read $0.50/M · Cache write $0.50/M
- Image
- $0.0672 per request
- Web search
- $0.014 per request
The provider's list price. We do not charge for searches yet.
65.5K context65.5K max out
Speed
- fastest over 24 hours
- 1.0k t/s
Fastest: Google
- Google862 ms to first token1.0k t/smedian of 23
Served
- served in the last 24 hours
- 100.00%
Across 1 provider, 24 of 24 requests
- Google100.00% · 24 of 24
Rebuilt once a day from the requests we sent, so it is a daily figure and not a live one.
Not yet. These figures come from Artificial Analysis, which the publish pipeline reads once a day.
Integrations
What the model holds, rather than a compatibility grade: nothing here measures how well a particular tool gets on with it, so nothing here scores one.
- answers on
- chat completions
- accepts
- textimagevideopdf
- returns
- textimage
- response_format
- web_search
Use this model
Works with the OpenAI SDK. Point it at our base URL and use this id.
curl https://api.hopscotchlabs.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google-aistudio/gemini-3.1-flash-image",
"messages": [{"role": "user", "content": "Hello"}],
"max_tokens": 256
}'