Gemini 3.1 Flash-Lite

低延迟、高性价比的多模态模型，适用于大规模、轻量的工作。

Googlegemini-3.1-flash-lite2026-05-07报告数据错误

规格

上下文: 1.05M
最大输出: 65.5K
输入价: $0.25/ 百万 Token
输出价: $1.5/ 百万 Token
发布日期: 2026-05-07

上下文

上下文: 1.05M
最大输入: 1.05M
最大输出: 65.5K

价格 · USD / 百万 Token

输入: $0.25
输出: $1.5
缓存读取: $0.025
缓存写入: —

输入输出

输入: 文本图像视频音频文档
输出: 文本

API

接口类型: generatebatch

思考

支持思考: 支持
思考等级: —

源信息

状态: 即将下线
发布日期: 2026-05-07
知识截止: —

能力

已确认: toolsstructured_outputstreamingcachingbatch

调用方式

googlemodel = gemini-3.1-flash-litereasoning = generationConfig.thinkingConfig.thinkingLevel

generate

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

batch

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

JSON

gemini-3.1-flash-lite.json

{
  "id": "gemini-3.1-flash-lite",
  "object": "model",
  "created": 1778112000,
  "owned_by": "google",
  "name": "Gemini 3.1 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": 0.25,
    "output": 1.5,
    "cache_read": 0.025,
    "cache_write": null
  },
  "features": [
    "tools",
    "structured_output",
    "streaming",
    "caching",
    "batch"
  ],
  "info": {
    "status": "deprecated",
    "release_date": "2026-05-07",
    "knowledge_cutoff": null,
    "description": "Low-latency, cost-effective multimodal model for high-volume, lightweight work.",
    "docs": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite",
    "verified_at": "2026-10-11"
  }
}

官方来源