GoogleUpdated 2h ago

Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) API Pricing

Live token cost for Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) from Google. Use the figures below for budgeting, then tune your exact request mix in the interactive calculator. Prices refresh every 24 hours from OpenRouter.

Input
$0.500
/ 1M tokens
Output
$3.00
/ 1M tokens
Cached input
Not supported

Capabilities

66K context66K max outputVision

Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) cost at scale

Estimated monthly cost across common production volumes. Assumes 30-day months and the request shapes shown.

TierRequests / dayIn / out tokens$ / month
Hobby1,000500 / 200$25.50
Startup10,0001,500 / 500$675.00
Growth100,0003,000 / 800$11,700.00
Enterprise1,000,0008,000 / 2,000$300,000.00
Open Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) in interactive calculator →

Compare Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) vs.

Frequently asked questions

How much does Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) cost?

Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) costs $0.50 per 1M input tokens and $3.00 per 1M output tokens. A typical 1,500-token in / 500-token out request costs $0.00225.

Does Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) support cached input?

No. Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) does not currently expose cached-input pricing through Google. Every input token is billed at the full rate.

What is the Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) context window?

Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) supports a context window of 65,536 tokens (66K). Max output per response is 65,536 tokens.

What is Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) good for?

Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) is a good fit for long context (1M+ tokens), multimodal grounding, document QA. For other use cases, run your specific input/output mix through the interactive calculator to compare against alternative models.