Gemini 2.5 Flash-Lite API Cost Calculator

Google's Gemini 2.5 Flash-Lite: $0.1/M input · $0.4/M output · $0.01/M cached input. Price your own workload below.

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

Presets:

What Gemini 2.5 Flash-Lite costs in practice

WorkloadInputOutputCost
Short chat message500250$0.0001
10-page document + summary7,000500$0.0009
Agent / coding session50,00010,000$0.0090
1M tokens in + 1M out1,000,0001,000,000$0.500

Gemini 2.5 Flash-Lite vs nearest rivals

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

ModelInput $/MTokOutput $/MTokMixed request
Gemini 2.5 Flash-Lite$0.1$0.4$0.0018
GPT-5 nano$0.05$0.4$0.0013
DeepSeek V4 Flash$0.14$0.28$0.0020
GPT-4o mini$0.15$0.6$0.0027

Frequently asked questions

How much does the Gemini 2.5 Flash-Lite API cost?

Gemini 2.5 Flash-Lite costs $0.1 per million input tokens and $0.4 per million output tokens, with cached input at $0.01 per million (90% off). Note: Cached input also incurs $1.00/MTok/hour storage.

How much does a typical chat message cost with Gemini 2.5 Flash-Lite?

A short chat message (about 500 input and 250 output tokens) costs roughly $0.0001 with Gemini 2.5 Flash-Lite. At 1,000 such requests a day, that is about $4.50 per month.

Is Gemini 2.5 Flash-Lite cheap compared to similar models?

Gemini 2.5 Flash-Lite has the #2 cheapest input rate of the 26 models we track. On a mixed workload (10K input / 2K output), it costs $0.0018 per request, versus $0.0013 for GPT-5 nano and $0.0020 for DeepSeek V4 Flash.

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.