ModelInfo
English
All models

Gemini 3.5 Flash-Lite

Low-cost, low-latency multimodal model for high-throughput workloads such as subagent tasks and document parsing.

Googlegemini-3.5-flash-lite2026-07-21Report incorrect data

Specs

Context
1.05M
Max output
65.5K
Input price
$0.3/ 1M tokens
Output price
$2.5/ 1M tokens
Released
2026-07-21

Context

Context window
1.05M
Max input
1.05M
Max output
65.5K

Pricing · USD / 1M tokens

Input
$0.3
Output
$2.5
Cache read
$0.03
Cache write
—

Modalities

Input
TextImageVideoAudioDocument
Output
Text

API

API types
generatebatch

Reasoning

Reasoning
Yes
Levels
—

Info

Status
Active
Released
2026-07-21
Knowledge cutoff
2026-03

Features

Confirmed
toolsstructured_outputstreamingcachingbatch
Source · official docsVerified 2026-10-11

How to call

1 provider

googlemodel = gemini-3.5-flash-litereasoning = generationConfig.thinkingConfig.thinkingLevel

generate
POSThttps://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent
batch
POSThttps://generativelanguage.googleapis.com/v1beta/models/{model}:batchGenerateContent

JSON

Standard format
gemini-3.5-flash-lite.json
{
  "id": "gemini-3.5-flash-lite",
  "object": "model",
  "created": 1784592000,
  "owned_by": "google",
  "name": "Gemini 3.5 Flash-Lite",
  "api": {
    "types": [
      "generate",
      "batch"
    ]
  },
  "limits": {
    "context": 1048576,
    "input": 1048576,
    "output": 65536
  },
  "modalities": {
    "input": [
      "text",
      "image",
      "video",
      "audio",
      "document"
    ],
    "output": [
      "text"
    ]
  },
  "reasoning": {
    "supported": true,
    "efforts": []
  },
  "pricing": {
    "currency": "USD",
    "unit": "1M_tokens",
    "input": 0.3,
    "output": 2.5,
    "cache_read": 0.03,
    "cache_write": null
  },
  "features": [
    "tools",
    "structured_output",
    "streaming",
    "caching",
    "batch"
  ],
  "info": {
    "status": "active",
    "release_date": "2026-07-21",
    "knowledge_cutoff": "2026-03",
    "description": "Low-cost, low-latency multimodal model for high-throughput workloads such as subagent tasks and document parsing.",
    "docs": "https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite",
    "verified_at": "2026-10-11"
  }
}

Official sources

7
Gemini 3.5 Flash-Lite | Gemini APIai.google.dev2026-10-10Models | Gemini APIai.google.dev2026-10-10Pricing | Gemini APIai.google.dev2026-10-10Deprecations | Gemini APIai.google.dev2026-10-10Generating content | Gemini APIai.google.dev2026-10-10Batch API | Gemini APIai.google.dev2026-10-10Gemini 3.5 Flash-Lite - Model Card — Google DeepMinddeepmind.google2026-10-11