Promptimizer

Route each prompt to the best model for the job.

Classify the ask, step up when quality slips, and measure spend against always-frontier — same OpenAI-compatible API.

Classify

Know the ask before you spend.

Each request gets a complexity score and a quality risk before any model is called.

Route

Economy when the ask is light. Frontier when it isn't. Escalate only when the answer fails the gate.

Measure

Cache repeated prefixes, record cost versus always-frontier, and keep a quality gate on every answer.

OpenAI-compatible.

Drop-in chat completions from the SDK, CLI, or curl.

1	import { Promptimizer } from "promptimizer";
2
3	const client = new Promptimizer({
4	apiKey: process.env.PROMPTIMIZER_API_KEY,
5	});
6
7	const res = await client.chat.completions.create({
8	messages: [{ role: "user", content: "What is 17 * 24?" }],
9	});
10
11	console.log(res.choices[0].message.content);
12	console.log(res.usage.cost);

Create an account, mint a pmz_live_ key, and route from the console, SDK, or CLI.