Workers AI

Portkey provides a robust and secure gateway to facilitate the integration of various Large Language Models (LLMs) into your applications, including Workers AI.

With Portkey, you can take advantage of features like fast AI gateway access, observability, prompt management, and more, all while ensuring the secure management of your LLM API keys through a virtual key system.

​

Portkey SDK Integration with Workers AI Models

Portkey provides a consistent API to interact with models from various providers. To integrate Workers AI with Portkey:

​

1. Install the Portkey SDK

Add the Portkey SDK to your application to interact with Workers AI’s API through Portkey’s gateway.

• NodeJS
• Python

npm install --save portkey-ai

​

2. Initialize Portkey with the Virtual Key

To use Workers AI with Portkey, get your API key from here, then add it to Portkey to create the virtual key.

• NodeJS SDK
• Python SDK

import Portkey from 'portkey-ai'

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
    virtualKey: "VIRTUAL_KEY" // Your Workers AI Virtual Key
})

​

3. Invoke Chat Completions with Workers AI

Use the Portkey instance to send requests to Workers AI. You can also override the virtual key directly in the API call if needed.

• NodeJS SDK
• Python SDK

const chatCompletion = await portkey.chat.completions.create({
    messages: [{ role: 'user', content: 'Say "this is a test"' }],
    model: '@cf/meta/llama-3.2-3b-instruct',
});

console.log(chatCompletion.choices);

​

Managing Workers AI Prompts

You can manage all prompts to Workers AI in the Prompt Library. All the current models of Workers AI are supported and you can easily start testing different prompts.

Once you’re ready with your prompt, you can use the portkey.prompts.completions.create interface to use the prompt in your application.

The complete list of features supported in the SDK are available on the link below.

You’ll find more information in the relevant sections:

1. Add metadata to your requests
2. Add gateway configs to your Workers requests
3. Tracing Workers AI requests
4. Setup a fallback from OpenAI to Workers AI APIs