# Gemini 3.1 Pro

> Google's most intelligent Gemini model with improved reasoning, a medium thinking level, and a 1M token context window.

**ID**: `google/gemini-3.1-pro`  
**Creator**: Google  
**Category**: text  
**Context**: 1M tokens  
**Pricing**: $2.00 / $12.00 per 1M · billed by your provider (BYOK)  
**Released**: 2026-02-19  
**Web page**: https://anyrouter.dev/model/google/gemini-3.1-pro

**Input modalities**: text, image  
**Output modalities**: text  

**Tokenizer**: Gemini

**Capabilities**: chat, streaming, reasoning, function-calling, vision, coding

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/gemini-3.1-pro",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| opencode-zen-byok | $2.00/M (list) | $12.00/M (list) |
| google-aistudio-byok | $2.00/M (list) | $12.00/M (list) |
| google-agent-platform-byok | $2.00/M (list) | $12.00/M (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Benchmarks

- **GPQA Diamond**: 0.9
- **HLE**: 0.4
- **τ²-Bench Telecom**: 1.0
- **SciCode**: 0.6
- **OTIS Mock AIME**: 1.0
- **SimpleQA (verified)**: 0.8

Benchmark data from [Epoch AI](https://epoch.ai/benchmarks) (CC-BY 4.0).