ModelInfo
English
All models

Gemini 3.1 Pro Preview

Pro model with improved thinking and token efficiency for advanced reasoning and agentic coding.

Googlegemini-3.1-pro-preview2026-02-19Report incorrect data

Specs

Context
1.05M
Max output
65.5K
Input price
$2/ 1M tokens
Output price
$12/ 1M tokens
Released
2026-02-19

Context

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

Pricing · USD / 1M tokens

Input
$2
Output
$12
Cache read
$0.2
Cache write
—

Modalities

Input
TextImageVideoAudioDocument
Output
Text

API

API types
generatebatch

Reasoning

Reasoning
Yes
Levels
—

Info

Status
Preview
Released
2026-02-19
Knowledge cutoff
—

Features

Confirmed
toolsstructured_outputstreamingcachingbatch
Source · official docsVerified 2026-10-10

How to call

1 provider

googlemodel = gemini-3.1-pro-previewreasoning = 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-3.1-pro-preview.json
{
  "id": "gemini-3.1-pro-preview",
  "object": "model",
  "created": 1771459200,
  "owned_by": "google",
  "name": "Gemini 3.1 Pro Preview",
  "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": 2,
    "output": 12,
    "cache_read": 0.2,
    "cache_write": null
  },
  "features": [
    "tools",
    "structured_output",
    "streaming",
    "caching",
    "batch"
  ],
  "info": {
    "status": "preview",
    "release_date": "2026-02-19",
    "knowledge_cutoff": null,
    "description": "Pro model with improved thinking and token efficiency for advanced reasoning and agentic coding.",
    "docs": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview",
    "verified_at": "2026-10-10"
  }
}

Official sources

6