gemini-3-5-flash-lite

Model overview

Only one rung of the Gemini lineup is priced for volume: $0.30 per million input tokens and $2.50 per million output, against $1.50 and $9 one step up and $2 and $12 on the Pro preview. Input is where the gap widens most, five times under Flash and a little under seven times under Pro, while output sits 3.6 times under Flash and 4.8 times under Pro. So gemini-3-5-flash-lite earns its place on read-heavy, write-light traffic: classification, extraction, routing, tagging. It is also the only rung whose output rate exceeds its input rate by more than eight to one, against six to one elsewhere, so verbose answers erode the saving fastest. Cached input is $0.03, with storage billed separately.

Billing conditions: Standard paid price. Cache storage is billed separately by Google.

Context window

0 tokens

Knowledge cutoff

—

Price last verified

2026-09-06

First observed

2026-08-11

Descriptions, capabilities, and tariffs come from the linked source. First-party prices take priority; OpenRouter fallbacks are labelled.