A drop-in OpenAI replacement that routes every request to the cheapest model that gets the job done. One line change, instant savings.
npm install @plagtech/pordl
90% of API calls don't need a frontier model. PORDL routes them to cheaper models automatically — same quality, fraction of the price.
Cost per 1M input tokens for a simple lookup task
Your existing OpenAI SDK code works as-is. Swap the base URL and PORDL handles the rest.
const client = new OpenAI({ apiKey: 'sk-your-openai-key', }); // Every request → GPT-4o // Full price, every time
const client = new OpenAI({ apiKey: 'pd_live_your-key', baseURL: 'https://api.pordl.dev/v1', }); // PORDL routes smart → 40-70% less
Simple tasks go to fast, cheap models. Complex tasks go to powerful ones. You save on every call without losing quality.
Identical requests return cached results instantly at zero cost. Repetitive workloads see 30-50% additional savings.
If a model is down, PORDL routes to the next best option. Your app stays up, no code changes needed.
Track exactly how much you're saving in real time. See per-model breakdowns, cache hit rates, and daily cost comparisons.
Same request format, same response format. Works with every OpenAI SDK and library. Python, Node, Go, Rust — all of them.
No per-token markup. No surprise bills. Predictable monthly pricing so you can budget without a spreadsheet.
7-day free trial on all plans. Cancel anytime.
PORDL analyzes each request's complexity and picks the right model. Simple lookups don't need frontier pricing.
| Model | Tier | Input cost | Output cost | Routes when |
|---|---|---|---|---|
| gpt-4o-mini | BUDGET | $0.15 / 1M tokens | $0.60 / 1M tokens | Simple tasks, lookups, formatting |
| gpt-4o | MID | $2.50 / 1M tokens | $10.00 / 1M tokens | Coding, writing, analysis |
| gpt-5.4 | FRONTIER | $3.00 / 1M tokens | $12.00 / 1M tokens | Complex reasoning, multi-step |
One line of code. Start saving now.
Get Your API Key →