---
title: A few ways to access to Generative AI and LLM
url: https://calvin.my/posts/a-few-ways-to-access-to-generative-ai-and-llm
published: 2025-01-12
updated: 2026-09-17
category: AI
tags:
- llm
- API
summary: 'The post outlines four ways to use generative AI and large language models: hosted services from major providers, locally run models through desktop tools, AI models embedded in browsers, and metered APIs for proprietary models. Hosted platforms commonly offer free and paid tiers, while local use depends on available hardware and model choice. API access supports application integration but is billed according to usage.'
---

# A few ways to access to Generative AI and LLM

There are many ways to access Generative AI and LLM features. This article demonstrates several of them.

## 1) AI Services

AI companies such as Google (Gemini), OpenAI (ChatGPT), Microsoft (Copilot), and Anthropic (Claude) provide services that allow users to interact with Generative AI. These services often include a free tier with usage caps, and paid plans to unlock additional capacities and capabilities. This is currently the most common way people interact with Generative AI.

![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/0fd0cd07-4ec5-4b26-9829-8e4705d0ea79.png)

## 2) Run locally

Tools like Ollama, AnythingLLM, and LM Studio enable users to run LLM models locally on their machines. The performance depends on the hardware specifications of your machine and the LLM models you select.

1. Download Ollama at [https://ollama.com/download](https://ollama.com/download)

2. Select a suitable model to run. The download will start automatically if you have not used the model before.

   ```bash
   ollama run phi4
   ```

3. Start using it!

   ```bash
   % ollama run phi4
   >>> hey
   Hello! How can I assist you today? If you have any questions or need information, feel free to let me know.

   >>>
   ```

4. Access Ollama via API if needed.

   ![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/020b11db-76bc-4a88-9605-75115561e5c7.png)

5. View all downloaded models using the command:

   ```bash
   % ollama list
   NAME             ID              SIZE      MODIFIED          
   phi4:latest      ac896e5b8b34    9.1 GB    About an hour ago    
   gemma2:latest    ff02c3702f32    5.4 GB    5 days ago           
   llama3.1:8b      46e0c10c039e    4.9 GB    7 days ago           
   llama3.2:3b      a80c4f17acd5    2.0 GB    7 days ago
   ```

## 3) Embedded Models in Browsers

Some browsers now include embedded AI models. For more details, refer to the previous articles:

https://calvin.my/posts/api-updates-on-chrome-on-device-ai-nov-2024

![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/e67bef56-b791-43a6-8b6d-4e889dc78877.png)

## 4) Metered API Access

Proprietary models, such as OpenAI's GPT-4o, GPT-o1, Claude Haiku, and Gemini Pro can be accessed via APIs provided by the respective service providers. These APIs are typically metered, and usage is billed based on the volume of requests.

![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/1952c3ea-5601-469b-a7e5-1be7fcc32f4a.png)