Gemini 3 Flash API Pricing

Gemini 3 Flash by Google costs $0.50 per million input tokens and $3.00 per million output tokens.

Price verified from Google's pricing page.

Rates and limits

Input / 1M
$0.50
Output / 1M
$3.00
Cached input / 1M
$0.05
Batch discount
50% off
Context window
1.05M tokens
Released
March 2026

Pricing note: Priced as gemini-3-flash-preview. Audio input is $1.00 (cached $0.10). Google now calls this its legacy Flash model and recommends gemini-3.6-flash.

What Gemini 3 Flash costs per month

Token volume split 3:1 between input and output, with no prompt caching.

Tokens per monthInput / outputStandardBatch API
1M750K / 250K$1.13$0.56
10M7.5M / 2.5M$11.25$5.63
100M75M / 25M$112.50$56.25
Estimate your own workload with Gemini 3 Flash

Where to run Gemini 3 Flash

Prices above are Google's direct rates. Cloud platforms can charge differently; the cloud platform view compares them.

Gemini 3 Flash pricing FAQ

How much does Gemini 3 Flash cost per million tokens?

Gemini 3 Flash costs $0.50 per million input tokens and $3.00 per million output tokens, as listed on Google's pricing page on September 30, 2026.

How much does Gemini 3 Flash cost for 10 million tokens a month?

About $11.25 a month, assuming 7.5 million input and 2.5 million output tokens with no prompt caching, or $5.63 through the batch API.

What is the context window of Gemini 3 Flash?

Gemini 3 Flash accepts up to 1,048,576 tokens of context.

Does Gemini 3 Flash support prompt caching?

Yes. Cached input tokens cost $0.05 per million, 90% less than the standard input rate.

Is there a batch discount for Gemini 3 Flash?

Yes. Requests sent through the batch API cost 50% less: $0.25 per million input tokens and $1.50 per million output tokens.

Where can I use the Gemini 3 Flash API?

Gemini 3 Flash is available through Google AI Studio (Gemini API), Google Cloud Vertex AI, and OpenRouter.

Compare with other models

Prices shown as input / output per million tokens. All model prices · Side-by-side comparison