# Google Gemini 3.1 Pro Preview API

> Gemini 3.1 Pro Preview is the Pro-tier reasoning model of Google's Gemini 3 series, released in February 2026 to refine Gemini 3 Pro with better thinking, improved token efficiency and more grounded, factually consistent answers. Google optimizes it for software engineering and for agentic workflows that need precise tool use and reliable multi-step execution across real-world domains. It accepts text, image, video, audio and PDF input, remains a preview model, and is Google's recommended replacement for the retired Gemini 3 Pro Preview.

Source: https://www.sandbase.ai/models/google/gemini-3.1-pro-preview
API reference: https://www.sandbase.ai/models/google/gemini-3.1-pro-preview/docs

## Facts

- Provider: Google
- Type: Language model
- Model ID: `google/gemini-3.1-pro-preview`
- Price: $1.70 per 1M input tokens, $10.20 per 1M output tokens (15% off list price)
- Context window: 1M tokens, up to 65.5K output tokens
- Capabilities: chat, vision, audio input, reasoning, structured output, function calling
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

- Chat Completions API: `POST https://api.sandbase.ai/v1/chat/completions`

```bash
curl -X POST https://api.sandbase.ai/v1/chat/completions \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/gemini-3.1-pro-preview",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 2048
}'
```

## FAQ

### How do I call Google Gemini 3.1 Pro Preview through SandBase?

Create a SandBase API key, then send requests with the model ID "google/gemini-3.1-pro-preview" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

### How much does Google Gemini 3.1 Pro Preview cost?

$1.70 per 1M input tokens and $10.20 per 1M output tokens with the current 15% discount (list price $2 / $12), billed per request from your SandBase balance.

### What is the context window of Google Gemini 3.1 Pro Preview?

1M tokens of context, with up to 65.5K output tokens per response.

### How does Google Gemini 3.1 Pro Preview score on benchmarks?

Google Gemini 3.1 Pro Preview scores 29.7 on the Artificial Analysis Intelligence Index (v4.3), ranking #42 of 83 models on SandBase; Coding Index 68.8, Agentic Index 8.2. Source: Artificial Analysis, measured as Gemini 3.1 Pro Preview.

### Which features does Google Gemini 3.1 Pro Preview support?

Google Gemini 3.1 Pro Preview supports vision (image input), reasoning, function calling, structured output. See Specifications above for the full list.

### Do I need a separate Google account?

No. One SandBase API key and balance gives you access to Google Gemini 3.1 Pro Preview and the other models in the catalog; you do not need to sign up with Google separately.