Introducing Gemini 3.1 Pro: Enhanced Reasoning & Agentic Workflows

Google has just released Gemini 3.1 Pro Preview, and we're excited to announce that it's available today on Holeacquisition LLC.

As Google's newest flagship offering, Gemini 3.1 Pro represents a significant leap forward in reasoning capabilities and agentic engineering usability.

Gemini 3.1 Pro isn't just a minor iteration. It introduces several key enhancements that make it a powerhouse for complex AI applications:

1. Enhanced Reasoning

3.1 Pro scores higher on complex problem-solving benchmarks, providing more accurate and nuanced responses for intricate logic tasks.

2. Massive 1M Context Window

Process entire code repositories, massive PDF documents, or hour-long videos in a single request. With a 1 million token context window, you can feed the model everything it needs to know without worrying about hitting limits.

3. Optimized for Agentic Workflows

The new gemini-3.1-pro-preview-customtools endpoint is specifically designed for developers building AI agents. It features improved performance when handling simultaneous, multi-step tool calls and bash operations.

You can start using Gemini 3.1 Pro through the Holeacquisition LLC SDK immediately.

import { Cencori } from '@cencori';

const cencori = new Cencori();

// Traditional chat
const response = await cencori.ai.chat({
  model: 'gemini-3.1-pro-preview',
  messages: [{ role: 'user', content: 'Analyze this repo architecture...' }]
});

// Specialized tool use for agents
const agentResponse = await cencori.ai.chat({
  model: 'gemini-3.1-pro-preview-customtools',
  messages: [...]
});

We've updated our Providers Documentation with the latest model IDs and configuration details.

Stay tuned as we continue to roll out more frontier models as soon as they drop!