google/gemini-3.1-flash-lite-preview

Name: google/gemini-3.1-flash-lite-preview
Author: Perplexity

proprietary

Our most cost-efficient multimodal model, offering the fastest performance for high-frequency, lightweight tasks. Gemini 3.1 Flash-Lite is best for high-volume agentic tasks, simple data extraction, and extremely low-latency applications where budget and speed are the primary constraints.

Context

1.0M

Max output

66K

Input price

$0.25/1M tokens

Output price

$1.5/1M tokens

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Details

ProviderPerplexity

CreatorGoogle AI

Familygemini-3.1

Licenseproprietary

Parameters—

Statusactive

Input modalitiestext

Output modalitiestext

Architecture—

Knowledge cutoff2025-01

Training data cutoff—

Release date—

Deprecation date—

Typechat

Reasoning tokens—

Max input—

Open weightNo

Sourceofficial

Last updated2026-05-14

Pricing

Input

$0.25

Output

$1.5

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Family Comparison: gemini-3.1

Model	Caps	Perf	Speed	Context	Max out	Pricing
google/gemini-3.1-flash-lite-preview	RVTS	—	—	1.0M	66K	$0.25$1.5
google/gemini-3.1-flash-lite	RVTS	—	—	1.0M	66K	$0.25$1.5
google/gemini-3.1-pro-preview	RVTS	—	—	1.0M	66K	$2$12

API

GET/v1/models/perplexity/google/gemini-3.1-flash-lite-preview