Gemini 3.6 Flash API Cost Calculator

Google's Gemini 3.6 Flash: $1.5/M input · $7.5/M output · $0.15/M cached input. Price your own workload below.

Cached input also incurs $1.00/MTok/hour storage.

Presets:

What Gemini 3.6 Flash costs in practice

WorkloadInputOutputCost
Short chat message500250$0.0026
10-page document + summary7,000500$0.014
Agent / coding session50,00010,000$0.150
1M tokens in + 1M out1,000,0001,000,000$9.00

Gemini 3.6 Flash vs nearest rivals

Closest-priced alternatives on a mixed 10K-input / 2K-output request:

ModelInput $/MTokOutput $/MTokMixed request
Gemini 3.6 Flash$1.5$7.5$0.030
Mistral Medium 3.5$1.5$7.5$0.030
GPT-5$1.25$10$0.033
o3$2$8$0.036

Frequently asked questions

How much does the Gemini 3.6 Flash API cost?

Gemini 3.6 Flash costs $1.5 per million input tokens and $7.5 per million output tokens, with cached input at $0.15 per million (90% off). Note: Cached input also incurs $1.00/MTok/hour storage.

How much does a typical chat message cost with Gemini 3.6 Flash?

A short chat message (about 500 input and 250 output tokens) costs roughly $0.0026 with Gemini 3.6 Flash. At 1,000 such requests a day, that is about $78.75 per month.

Is Gemini 3.6 Flash cheap compared to similar models?

Gemini 3.6 Flash has the #15 cheapest input rate of the 26 models we track. On a mixed workload (10K input / 2K output), it costs $0.030 per request and $0.033 for GPT-5.

Related

Compare all models at once ·Count tokens in your prompt

Last updated 2026-08-03. Prices verified againstGoogle's official pricing page; see themethodology.