Portkey Integration

Portkey is an AI infrastructure platform that provides a unified gateway for managing multiple LLM providers. It offers observability, reliability features like load balancing and fallbacks, access control, and the ability to bring your own privately-hosted models.

Portkey's BYOLLM (Bring Your Own LLM) feature lets you register LLM API as a custom provider, routing requests through Portkey's gateway while accessing all LLM API models.

Prerequisites

An LLM API account with an API key
Portkey installed or accessible

Setup

Get Your LLM API Key

Log in to your LLM API dashboard
Click Create Key to Start
Copy your new API key immediately — it will only be shown once
Store the key securely (e.g., in a password manager or .env file)

INFO

LLM API is an OpenAI-compatible gateway that gives you access to dozens of AI models through a single API key and endpoint.

Configure LLM API in Portkey

Option A --- Using the Model Catalog (UI)

Log in to your Portkey dashboard.
Navigate to Model Catalog → Add Provider.
Enable the "Local/Privately hosted provider" toggle.
Select OpenAI as the matching API spec.
Enter the following:
- Custom Host: https://api.llmapi.ai/v1
- Authorization Header: Bearer your-llm-api-key-here
Name your provider (e.g., "LLM API") and click "Create".

Option B --- Direct Integration (code)

const portkey = new Portkey({
  apiKey: "PORTKEY_API_KEY",
  provider: "openai",
  customHost: "https://api.llmapi.ai/v1/",
  Authorization: "Bearer your-llm-api-key-here",
  forwardHeaders: ["Authorization"],
});

Test the Integration

Verify that Portkey can successfully communicate with LLM API by sending a test request. All requests will now be routed through LLM API.

INFO

Once configured, Portkey adds observability, caching, and fallback routing on top of LLM API --- ideal for production deployments.

Benefits of Using LLM API with Portkey

Multi-Provider Access: Use models from OpenAI, Anthropic, Google, and more through a single API
Cost Control: Track and limit your AI spending with detailed usage analytics
Unified Billing: One account for all providers instead of managing multiple API keys
Caching: Reduce costs with response caching for repeated requests

INFO

View all available models on the models page.