GoogleUpdated 2h ago

Google: Nano Banana (Gemini 2.5 Flash Image) API Pricing

Live token cost for Google: Nano Banana (Gemini 2.5 Flash Image) 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
$0.300
/ 1M tokens
Output
$2.50
/ 1M tokens
Cached input
$0.030
/ 1M tokens

Capabilities

33K context33K max outputVisionPrompt cachingReasoning tokens

Google: Nano Banana (Gemini 2.5 Flash Image) 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$19.50
Startup10,0001,500 / 500$510.00
Growth100,0003,000 / 800$8,700.00
Enterprise1,000,0008,000 / 2,000$222,000.00
Open Google: Nano Banana (Gemini 2.5 Flash Image) in interactive calculator →

Compare Google: Nano Banana (Gemini 2.5 Flash Image) vs.

Frequently asked questions

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

Google: Nano Banana (Gemini 2.5 Flash Image) costs $0.30 per 1M input tokens and $2.50 per 1M output tokens, with cached input at $0.03 per 1M tokens. A typical 1,500-token in / 500-token out request costs $0.00170.

Does Google: Nano Banana (Gemini 2.5 Flash Image) support cached input?

Yes. Google: Nano Banana (Gemini 2.5 Flash Image) supports prompt caching at $0.03 per 1M cached input tokens. Reuse the same system prompt or context across requests to cut input cost dramatically.

What is the Google: Nano Banana (Gemini 2.5 Flash Image) context window?

Google: Nano Banana (Gemini 2.5 Flash Image) supports a context window of 32,768 tokens (33K). Max output per response is 32,768 tokens.

What is Google: Nano Banana (Gemini 2.5 Flash Image) good for?

Google: Nano Banana (Gemini 2.5 Flash Image) is a good fit for fast multimodal tasks, video understanding, RAG over long documents. For other use cases, run your specific input/output mix through the interactive calculator to compare against alternative models.