---
title: "Gemini 3.1 Pro Preview | AI Models | Inference.net"
description: "Run Gemini 3.1 Pro Preview (Google) on Inference.net. 1.049M context. tool-calling, structured outputs, vision input, reasoning. Deploy with an OpenAI-compatible API and pay-per-token pricing."
url: "https://inference.net/models/gemini-3.1-pro-preview/"
---

Google Multimodal Model

# Gemini 3.1 Pro Preview

Google's Gemini 3 frontier reasoning model, refined for factual grounding and precise tool use. Optimized for software engineering and multi-step agentic workflows over a 1M-token context with text, image, audio, video, and PDF input.

[Get Started](https://inference.net/signin/) [Documentation](https://docs.inference.net)

Model details

Developed by Google

Context window 1024K tokens

Max output 64K tokens

Model API pricing Per 1M tokens

Input $2.00

Cache read $0.20

Output $12.00

[See all pricing](https://inference.net/pricing/)

```
import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.inference.net/v1",
  apiKey: "<YOUR_API_KEY>",
});

const completion = await openai.chat.completions.create({
  model: "gemini-3.1-pro-preview",
  messages: [
    {
      role: "user",
      content: "What is the meaning of life?"
    }
  ],
  stream: true,
});

for await (const chunk of completion) {
  process.stdout.write(chunk.choices[0]?.delta.content as string);
}
```

Prompt caching

1. Keep the stable system content block byte-identical across calls.
2. Mark it with cache_control: { "type": "ephemeral" } to set a cache point.
3. Long prompts are required. As a practical target, use roughly 4,000 stable tokens for Gemini 3.1 Pro Preview or 9,000 for the other listed Gemini models; these are not guaranteed provider minimums.
4. Check usage.prompt_tokens_details.cached_tokens in the response to confirm cache reads.

```
{
  "messages": [{
    "role": "system",
    "content": [{
      "type": "text",
      "text": "Stable system content...",
      "cache_control": { "type": "ephemeral" }
    }]
  }]
}
```

## Related models

[See all models](https://inference.net/models/)

Model

[Kimi K3 1024K input context Vision Tools Reasoning $3.00 / $15.00 2 variants](https://inference.net/models/kimi-k3/)

[MiniMax M3.1 Flash 977K input context Vision Tools Reasoning $0.10 / $0.50](https://inference.net/models/minimax-m3.1-flash/)

[Nemotron 3 Super 256K input context Tools $0.102 / $0.48](https://inference.net/models/nemotron-3-super/)

[Schematron V2 Small 125K input context $0.05 / $0.23](https://inference.net/models/schematron-v2-small/)

[Schematron V2 Turbo 125K input context $0.03 / $0.15](https://inference.net/models/schematron-v2-turbo/)

## Start building with Gemini 3.1 Pro Preview today

Serverless, OpenAI-compatible, and billed per token. No commitments.

[Get Started](https://inference.net/signin/) [Read the docs](https://docs.inference.net)