Skip to main content
Google Cloud logo

Gemini 3.5 Flash-Lite API pricing on Google Cloud

Every Google Cloud Gemini 3.5 Flash-Lite rate we track, compared against 6 providers serving the same model.

Input from /1M
$0.150
Output /1M
$1.25
Input price rank
#1 of 6
Last updated
November 21, 2026

The cheapest Gemini 3.5 Flash-Lite input price we currently track is $0.300/1M on GMI Cloud.

The cheapest Gemini 3.5 Flash-Lite output price is $2.50/1M on GMI Cloud.

Google Cloud Gemini 3.5 Flash-Lite rates

Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.

Google Cloud Gemini 3.5 Flash-Lite pricing by mode
ModeInputOutput
Batch$0.150/1M$1.25/1M
Standard$0.300/1M$2.50/1M

About Gemini 3.5 Flash-Lite

Creator
Google
Context
1.0M
Modalities
text, image, video, audio
Tool calling
Yes
Full Gemini 3.5 Flash-Lite details and every provider →Compare API pricing for every Gemini model →

Gemini 3.5 Flash-Lite on other providers

About Google Cloud

GCP provides powerful GPU instances with flexible pricing and integration with Google's AI and machine learning tools. It's a major cloud provider known for its innovation in Kubernetes, AI/ML, and data analytics.

Frequently Asked Questions

How much does Gemini 3.5 Flash-Lite cost on Google Cloud?

Google Cloud serves Gemini 3.5 Flash-Lite from $0.150 per 1M input tokens, across 2 tracked pricing modes. Prices are collected daily — see the table above for current input, output, and cached-input rates.

Is Google Cloud the cheapest way to run Gemini 3.5 Flash-Lite?

Google Cloud ranks #1 of 6 providers we track serving Gemini 3.5 Flash-Lite on input price. The cheapest input price right now is on GMI Cloud. The lowest output price is $2.50/1M on GMI Cloud. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.

Does Google Cloud offer batch or cached pricing for Gemini 3.5 Flash-Lite?

We track 2 Gemini 3.5 Flash-Lite offerings from Google Cloud. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.