Gemini 3.5 Flash-Lite

Gemini 3.5 Flash-Lite is Google's generally available, high-throughput Gemini model for latency-sensitive agents, search, extraction, and document processing.

Platform: Replicate

Language ModelMultimodalHigh ThroughputAgent WorkflowsLong ContextGoogle

Gemini API / Google AI Studio / Gemini Enterprise

Gemini API standard paid tier: $0.30 per million input tokens and $2.50 per million output tokens

Commercial

🚀Function Overview

Gemini 3.5 Flash-Lite provides a low-cost, high-throughput Gemini tier for repeated extraction, classification, search, document processing, and subagent workloads.

Key Features

Official GA Gemini API model ID gemini-3.5-flash-lite
1-million-token context window and 64K maximum output
Text, image, audio, and video input with text output
Minimal default thinking level with medium and high options for harder agent tasks
Built-in tools including Computer Use
Standard Gemini API pricing of $0.30 per million input tokens and $2.50 per million output tokens
March 2026 knowledge cutoff in the official model card
Google-reported throughput of 350 output tokens per second on the Artificial Analysis Index

Use Cases

•High-volume document extraction and structured JSON parsing
•Search, classification, translation, and summarization queues
•Repeated subagent execution under a stronger orchestrator
•Low-latency multimodal processing
•Production migration from Gemini 3.1 Flash-Lite or Gemini 2.5 Flash

⚙️Input Parameters

model

string

Use gemini-3.5-flash-lite for the generally available Gemini API model.

input

object

Interactions API input containing text or supported multimodal content such as images, audio, and video.

system_instruction

string

Optional system-level behavior and structured-output instruction.

thinking_level

string

Reasoning-effort control; minimal is the documented default for maximum throughput.

💡Usage Examples

Example 1

Input Parameters

{
  "model": "gemini-3.5-flash-lite",
  "input": "Extract the invoice date, supplier, currency, subtotal, tax, and total as JSON.",
  "thinking_level": "minimal"
}

Output Results

Gemini 3.5 Flash-Lite returns a text or structured response through the Gemini Interactions API. Validate schema adherence, throughput, and retry rate on representative documents before production use.

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: Gemini API / Google AI Studio / Gemini Enterprise
Commercial Use: Supported
Pricing: Gemini API standard paid tier: $0.30 per million input tokens and $2.50 per million output tokens
Platform: Replicate

Related Keywords

Gemini 3.5 Flash-Litegemini-3.5-flash-liteGoogle Gemini Flash LiteGemini 3.5 Flash-Lite APIGemini 3.5 Flash-Lite pricingGemini Flash-Lite context windowGemini 3.5 Flash-Lite vs 3.6 Flashhigh throughput Gemini model

Related Models

Bielik 1.5B v3 Instruct

Bielik-1.5B-v3-Instruct is a generative text model featuring 1.6 billion parameters. It is result of collaboration between the open-science/open-souce project SpeakLeash and the High Performance Computing (HPC)

Cordia-A6 Text Generation Model

A model for generating text sequences based on input prompts and adjustable parameters.

Claude Sonnet 4

Claude Sonnet 4 is a significant upgrade to 3.7, delivering superior coding and reasoning while responding more precisely to your instructions