← All skills
Models
⚡

Gemini 3.1 Pro

Google's reasoning champion, ~1M token context

What it is

Google's flagship: it leads scientific-reasoning benchmarks (GPQA Diamond) with a context window of roughly 1 million tokens. Multimodal and natively integrated into Google Workspace. For speed and low cost there's the Gemini 3.5 Flash variant. Free up to generous limits with the Gemini API.

How to use it, step by step

  1. 1

    Go to gemini.google.com for direct chat use, or ai.google.dev for the API.

  2. 2

    For the API get a free key from Google AI Studio (aistudio.google.com): generous to start.

  3. 3

    Upload huge documents or long transcripts: the ~1M token context handles entire books.

  4. 4

    Install the SDK: pip install google-genai and call the 'gemini-3.1-pro' model (or 'gemini-3.5-flash' to save).

  5. 5

    For logic and science problems it's among the best: give it the problem and ask it to reason step by step.

💡Practical tips

  • →For reasoning and science it tops the benchmarks: use it on the hard problems.
  • →For high-volume apps switch to Gemini 3.5 Flash: faster and cheaper.
  • →It integrates into Gmail, Docs, and Sheets if you use Google Workspace.

💰Pricing

Gemini free with limits; Advanced included in Google One AI Premium. API has a generous free tier, then per-token.

Go to Gemini 3.1 Pro

The official site opens in a new tab.