# LLMs

## Overview

LLM procedures in Kognitos offer a flexible and powerful interface for interacting with large language models (LLMs), including OpenAI’s GPT and Google’s Gemini. These procedures allow you to integrate advanced natural language understanding, generation, and reasoning directly into your automation workflows.

#### Capabilities

With LLM automation procedures, you can:

* **Generate Text** – Create summaries, explanations, or creative content based on prompts.
* **Answer Questions** – Return answers based on prompts or external document content.
* **Summarize Content** – Produce concise summaries of lengthy documents automatically.
* **Extract Information** – Identify and extract specific data points, key insights, or relevant details from text or documents.

## Available LLM Models

Here is a list of available models for LLM procedures in Kognitos.

{% hint style="success" %}
For most document processing tasks, we recommend using **Gemini Pro 2.5** (`gemini-2.5-pro`) for its accuracy and versatility.
{% endhint %}

<table><thead><tr><th width="156.94921875">Model Name</th><th width="301.45703125">Model Name in Kognitos</th><th width="112.1171875">Type</th><th>Availability Regions</th></tr></thead><tbody><tr><td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/2-5-pro">Gemini 2.5 Pro</a></td><td><code>gemini-2.5-pro</code></td><td>Gemini</td><td>US, EU, UK¹</td></tr><tr><td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/2-0-flash">Gemini 2.0 Flash</a></td><td><code>gemini-2.0-flash</code></td><td>Gemini</td><td>US, EU, UK¹</td></tr><tr><td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/2-0-flash-lite">Gemini 2.0 Flash Lite</a></td><td><code>gemini-2.0-flash-lite</code></td><td>Gemini</td><td>US, EU, UK¹</td></tr><tr><td><a href="https://platform.openai.com/docs/models/gpt-5">GPT-5</a></td><td><code>gpt-5</code></td><td>OpenAI</td><td>US, EU</td></tr><tr><td><a href="https://platform.openai.com/docs/models/gpt-5-mini">GPT-5 mini</a></td><td><code>gpt-5-mini</code></td><td>OpenAI</td><td>US, EU</td></tr><tr><td><a href="https://platform.openai.com/docs/models/gpt-5-nano">GPT-5 nano</a></td><td><code>gpt-5-nano</code></td><td>OpenAI</td><td>US, EU</td></tr><tr><td><a href="https://platform.openai.com/docs/models/gpt-4.1">GPT-4.1</a></td><td><code>gpt-4.1</code></td><td>OpenAI</td><td>US, EU, UK¹</td></tr><tr><td><a href="https://platform.openai.com/docs/models/gpt-4o-search-preview">GPT-4o Search Preview</a></td><td><p><code>gpt-4o-search-preview</code></p><p><br><strong>Note:</strong> GPT-4 Search Preview currently <em>cannot</em> process images or documents. It supports text input only.</p></td><td>OpenAI</td><td>US, EU, UK¹</td></tr><tr><td>GPT-4o Latest</td><td><code>gpt-4o-latest</code></td><td>OpenAI</td><td>US, EU, UK¹</td></tr><tr><td>GPT-4 Turbo Latest</td><td><code>gpt-4-turbo-latest</code></td><td>OpenAI</td><td>US</td></tr><tr><td><a href="https://platform.openai.com/docs/models/gpt-4-turbo">GPT-4 Turbo</a></td><td><code>gpt-4-turbo</code></td><td>OpenAI</td><td>US, EU, UK¹</td></tr><tr><td><a href="https://platform.openai.com/docs/models/gpt-4o-mini">GPT-4o mini</a></td><td><code>gpt-4o-mini</code></td><td>OpenAI</td><td>US, EU, UK¹</td></tr><tr><td><a href="https://platform.openai.com/docs/models/gpt-4o">GPT-4o</a></td><td><code>gpt-4o</code></td><td>OpenAI</td><td>US, EU, UK¹</td></tr><tr><td><a href="https://platform.openai.com/docs/models/gpt-4">GPT-4</a></td><td><code>gpt-4</code></td><td>OpenAI</td><td>US, EU, UK¹</td></tr><tr><td>GPT-4 Latest</td><td><code>gpt-4-latest</code></td><td>OpenAI</td><td>US</td></tr><tr><td>GPT-3.5 Turbo Latest</td><td><code>gpt-3.5-turbo-latest</code></td><td>OpenAI</td><td>US</td></tr><tr><td><a href="https://platform.openai.com/docs/models/gpt-3.5-turbo">GPT-3.5 Turbo</a></td><td><code>gpt-3.5-turbo</code></td><td>OpenAI</td><td>US</td></tr></tbody></table>

> **¹** *The model is available in the UK product instance—data is provided from the EU region.*

## API Keys & Credentials

To use your own API credentials, configure them through [**Bring Your Own Model (BYOM)**](/legacy/legacy-experience/automation-management/byom.md). This feature allows you to securely add and manage API keys and credentials for providers like OpenAI, Google Gemini, Anthropic Claude, and custom models at the agent level.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.kognitos.com/legacy/legacy-experience/automation-areas/llm.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.