PORDL API

Drop-in OpenAI replacement with smart model routing. Send requests to api.pordl.dev instead of api.openai.com, and PORDL routes each request to the cheapest model that can handle it.

Base URL for all API requests:

https://api.pordl.dev

All endpoints use JSON request/response bodies and follow OpenAI's API format — any OpenAI-compatible client works out of the box.

Quick Start

Node.js (SDK)

import Pordl from "@plagtech/pordl";

const client = new Pordl({ apiKey: "pd_live_..." });

const res = await client.chat.completions.create({
  model: "auto",
  messages: [{ role: "user", content: "Hello!" }],
});

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

Node.js (OpenAI SDK directly)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "pd_live_...",
  baseURL: "https://api.pordl.dev/v1",
});

Python

from openai import OpenAI

client = OpenAI(
    api_key="pd_live_...",
    base_url="https://api.pordl.dev/v1",
)

curl

curl https://api.pordl.dev/v1/chat/completions \
  -H "Authorization: Bearer pd_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Sign Up

Request

{
  "email": "you@example.com",     // required
  "password": "your-password"     // required
}

Response

{
  "message": "Account created",
  "user": {
    "id": "a15769e8-...",
    "email": "you@example.com",
    "tier": "free"
  },
  "api_key": "pd_live_6b7c140dd949cac44b14bb23b6cfa19a",
  "note": "Save this API key — it won't be shown again."
}

Log In

Request

{
  "email": "you@example.com",
  "password": "your-password"
}

API Keys

All authenticated requests require an API key in the Authorization header. Keys start with pd_live_ for production or pd_test_ for testing.

Authorization: Bearer pd_live_your_key_here

Keys are hashed and stored securely — PORDL never stores your raw key. If you lose your key, log in again to generate a new one.

Chat Completions

Request Body

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 8,
    "total_tokens": 20
  }
}

Models

Smart Routing

When you set model: "auto", PORDL classifies your request by complexity and routes it to the cheapest model that can handle it:

You can also pass a specific model name to bypass routing. The routing classification is returned in the x-pordl-complexity response header.

Response Headers

Every chat completion response includes routing metadata:

Pricing

Checkout

Request

// Header: Authorization: Bearer pd_live_...
{
  "tier": "starter"   // "starter" | "pro" | "scale"
}

Response

{
  "url": "https://checkout.stripe.com/c/pay/cs_live_...",
  "tier": "starter"
}

Customer Portal

Usage

Request

Authorization: Bearer pd_live_...

Errors

Errors follow a consistent JSON format:

{
  "error": {
    "message": "Invalid API key",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}

Rate Limits

Rate limits depend on your subscription tier:

Rate limit info is returned in response headers: x-ratelimit-limit-requests, x-ratelimit-remaining-requests, x-ratelimit-reset-requests.

SDK

Install the official Node.js SDK:

npm install @plagtech/pordl

The SDK is a thin wrapper around the OpenAI Node.js SDK — it sets baseURL to api.pordl.dev and handles auth. All OpenAI methods and types work as-is.

import Pordl from "@plagtech/pordl";

const client = new Pordl({ apiKey: "pd_live_..." });

const res = await client.chat.completions.create({
  model: "auto",
  messages: [{ role: "user", content: "What is 2+2?" }],
});

console.log(res.choices[0].message.content);
// "4"

For Python, use the standard OpenAI library with a custom base_url. See Quick Start for examples.

← Back to PORDL  ·  GitHub  ·  npm