Gemini 3.8 Flash

Most intelligent Flash model for long-horizon coding, agents and enterprise workflows.

Googlegemini-3.8-flash2026-09-02Report incorrect data

Specs

Context: 1.05M
Max output: 65.5K
Input price: $0.75/ 1M tokens
Output price: $3.75/ 1M tokens
Released: 2026-09-02

Context

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

Pricing · USD / 1M tokens

Input: $0.75
Output: $3.75
Cache read: $0.075
Cache write: —

Modalities

Input: TextImageVideoAudioDocument
Output: Text

API

API types: generatebatch

Reasoning

Reasoning: Yes
Levels: lowmediumhigh

Info

Status: Active
Released: 2026-09-02
Knowledge cutoff: 2026-03

Features

Confirmed: toolsstructured_outputstreamingcachingbatch

How to call

googlemodel = gemini-3.8-flashreasoning = generationConfig.thinkingConfig.thinkingLevel

generate

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

batch

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

JSON

gemini-3.8-flash.json

{
  "id": "gemini-3.8-flash",
  "object": "model",
  "created": 1788307200,
  "owned_by": "google",
  "name": "Gemini 3.8 Flash",
  "api": {
    "types": [
      "generate",
      "batch"
    ]
  },
  "limits": {
    "context": 1048576,
    "input": 1048576,
    "output": 65536
  },
  "modalities": {
    "input": [
      "text",
      "image",
      "video",
      "audio",
      "document"
    ],
    "output": [
      "text"
    ]
  },
  "reasoning": {
    "supported": true,
    "efforts": [
      "low",
      "medium",
      "high"
    ]
  },
  "pricing": {
    "currency": "USD",
    "unit": "1M_tokens",
    "input": 0.75,
    "output": 3.75,
    "cache_read": 0.075,
    "cache_write": null
  },
  "features": [
    "tools",
    "structured_output",
    "streaming",
    "caching",
    "batch"
  ],
  "info": {
    "status": "active",
    "release_date": "2026-09-02",
    "knowledge_cutoff": "2026-03",
    "description": "Most intelligent Flash model for long-horizon coding, agents and enterprise workflows.",
    "docs": "https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash",
    "verified_at": "2026-10-11"
  }
}

Official sources

Gemini 3.8 Flash | Gemini APIai.google.dev2026-10-10 Models | Gemini APIai.google.dev2026-10-10 Pricing | Gemini APIai.google.dev2026-10-10 Deprecations | Gemini APIai.google.dev2026-10-10 Generating content | Gemini APIai.google.dev2026-10-10 Batch API | Gemini APIai.google.dev2026-10-10 Gemini 3.8 Flash - Model Card — Google DeepMinddeepmind.google2026-10-11