Use the OpenAI SDK with Portrix to Access 400+ Models

Because Portrix implements the full OpenAI API specification, the official OpenAI SDKs work with Portrix out of the box — no monkey-patching, no custom wrappers. Point the client at Portrix’s base URL, swap in your Portrix API key, and every model on the platform becomes available through the same interface you already know.

Python

Install the openai package if you haven’t already:

pip install openai

Change the two highlighted lines to redirect all SDK calls through Portrix:

from openai import OpenAI

# Before
client = OpenAI(
    api_key="sk-...",  
)  

# After
client = OpenAI(
    api_key="your-portrix-api-key",  
    base_url="https://api.portrix.ai/v1",  
)

response = client.chat.completions.create(
    model="anthropic/claude-3-5-sonnet",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

JavaScript / TypeScript

Install the openai npm package if you haven’t already:

npm install openai

Apply the same two-line change in your TypeScript or JavaScript project:

import OpenAI from "openai";

// Before
const client = new OpenAI({
  apiKey: "sk-...",  
});  

// After
const client = new OpenAI({
  apiKey: process.env.PORTRIX_API_KEY,  
  baseURL: "https://api.portrix.ai/v1",  
});

const response = await client.chat.completions.create({
  model: "openai/gpt-4o",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.choices[0].message.content);

What changes and what doesn’t

Parameter	OpenAI	Portrix
Base URL	`https://api.openai.com/v1`	`https://api.portrix.ai/v1`
API key	OpenAI secret key (`sk-...`)	Portrix API key
Model names	`gpt-4o`, `gpt-3.5-turbo`, etc.	`provider/model` format, e.g. `openai/gpt-4o`
All other parameters	—	Unchanged
Response format	OpenAI response object	Unchanged

Model names use the provider/model format in Portrix — for example, openai/gpt-4o, anthropic/claude-3-5-sonnet, or google/gemini-2.0-flash. Pass these directly as the model field in your request.

Migrating existing code

Install or update the OpenAI SDK

Make sure you are on a recent version of the SDK. Portrix is compatible with openai >= 1.0.0 for Python and openai >= 4.0.0 for Node.js.

pip install --upgrade openai   # Python
npm install openai@latest      # Node.js

Set your Portrix API key

Store your key in an environment variable so it never appears in source code:

export PORTRIX_API_KEY="your-portrix-api-key"

Add this to your .env file for local development and configure it as a secret in your deployment environment.

Update the client initialization

Replace your existing client constructor with the Portrix-configured version:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["PORTRIX_API_KEY"],
    base_url="https://api.portrix.ai/v1",
)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.PORTRIX_API_KEY,
  baseURL: "https://api.portrix.ai/v1",
});

Everything else in your codebase — method calls, parameters, response parsing — stays exactly the same.

Use an environment variable for the base URL as well as the API key. Set OPENAI_BASE_URL=https://api.portrix.ai/v1 and OPENAI_API_KEY=$PORTRIX_API_KEY locally, and the OpenAI SDK will pick them up automatically — letting you switch between OpenAI and Portrix without touching a single line of application code.

Get Started

Core Concepts

Guides

Integrations

Configuration

Help

Use the OpenAI SDK with Portrix to Access 400+ Models

Python

JavaScript / TypeScript

What changes and what doesn’t

Migrating existing code

​Python

​JavaScript / TypeScript

​What changes and what doesn’t

​Migrating existing code

Python

JavaScript / TypeScript

What changes and what doesn’t

Migrating existing code