diff --git a/README.md b/README.md
index eb551f3..22180d0 100644
--- a/README.md
+++ b/README.md
@@ -1,10 +1,11 @@
-# openai api mock
+# OpenAI API mock / proxy Worker
 
-this project aims to convert / proxy Cloudflare Workers AI responses to OpenAI API compatible responses so Workers AI models can be used with any OpenAI / ChatGPT compatible client
+This project aims to convert/proxy Cloudflare Workers AI responses to OpenAI API compatible responses so that [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai/) models can be used with any OpenAI/ChatGPT compatible client.
 
-- supports streaming and non-streaming responses
-- rewrites the different models 'gpt-3' and 'gpt-4' to use `@cf/meta/llama-2-7b-chat-fp16`
-- if the openAI client can be configured to provide other model names, just put in the cloudflare model id instead of gpt-4
+- Supports streaming and non-streaming responses
+- Rewrites *default* models such as `gpt-3` and `gpt-4` to use `@cf/meta/llama-3-8b-instruct`
+- If the OpenAI client can be configured to use other model names, simply replace `gpt-4` with the Cloudflare model ID
+- Here's a list of all [Cloudflare Workers AI models](https://developers.cloudflare.com/workers-ai/models/)
 
 ## installation
 
@@ -14,17 +15,20 @@ this project aims to convert / proxy Cloudflare Workers AI responses to OpenAI A
 2. clone this repo
 3. run `npm run deploy`
 
-after the script has been deployed, you'll get an URL which you can use as your OpenAI API endpoint for other applications, something like this:
+after the script has been deployed, you'll get an URL which you can use as your OpenAI API endpoint for other applications, something like this: `https://openai-api.foobar.workers.dev`
 
-```
-https://openai-api.foobar.workers.dev
-```
+## examples
 
-## use with llm
+### use with llm
 
-- [read and install everything about llm here](https://llm.datasette.io/)
+I mainly created this project to make it work with the awesome [LLM project]((https://llm.datasette.io/)) from [Simon Willison](https://simonwillison.net/)
 
-create this file `~/Library/Application\ Support/io.datasette.llm/extra-openai-models.yaml`:
+- [go ahead and read everything about LLM here](https://llm.datasette.io/)
+- [how to install LLM](https://llm.datasette.io/en/stable/setup.html)
+- since LLM can work with [OpenAI-compatible models](https://llm.datasette.io/en/stable/openai-models.html#adding-more-openai-models), we're adding our OpenAI API proxy like this:
+
+1. find the directory of your llm configuration: `dirname "$(llm logs path)"`
+2. create this file: `vi ~/Library/Application\ Support/io.datasette.llm/extra-openai-models.yaml`
 
 ```yaml
 - model_id: cloudflare
@@ -32,14 +36,25 @@ create this file `~/Library/Application\ Support/io.datasette.llm/extra-openai-m
   api_base: 'https://openai-api.foobar.workers.dev/'
 ```
 
+you can also add multiple models there:
+
+```yaml
+- model_id: cfllama2
+  model_name: "@cf/meta/llama-2-7b-chat-fp16"
+  api_base: "https://openai-api.foobar.workers.dev"
+- model_id: cfllama3
+  model_name: "@cf/meta/llama-3-8b-instruct"
+  api_base: "https://openai-api.foobar.workers.dev"
+```
+
 use it with streaming (recommended):
 
 ```shell
-llm chat -m cloudflare
+llm chat -m cfllama3
 ```
 
 use it without streaming:
 
 ```shell
-llm chat --no-stream -m cloudflare
+llm chat --no-stream -m cfllama3
 ```