Before you spend money asking GPT-5.6…let Kimi inspect your prompt first.
Prompt Inspector automatically picks the cheapest GPT-5.6 tier that can nail your prompt — Luna for the small stuff, Terra for the workhorse jobs, Sol only when it's actually earned.
Point your SDK at it
One-line migration. Your code already speaks OpenAI — the proxy speaks it back, just cheaper.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "http://localhost:4000/v1", // ← the only change
});
const res = await client.chat.completions.create({
model: "gpt-5.6-auto", // Kimi picks the tier
messages,
});Everything the bill was hiding
Inspection, routing, and accounting — in one open-source box.
Paste any prompt, get a tier verdict with the reasoning to back it up — before you spend a cent.
Luna, Terra and Sol priced side by side on every request, down to the tenth of a cent.
Mechanical rewrites that drop your prompt a tier — savings verified by re-inspection, not vibes.
An OpenAI-compatible proxy. Change one baseURL line and every request rides the cheapest sufficient tier.
Every routed request logged with cost, savings and latency. Watch the Sol money come back.
Each routing decision ships with human-readable reasons. No black box, no hand-waving.
Run one prompt against all three tiers side by side and judge whether the cheap model keeps up.
Flags traffic riding Sol that the classifier says belongs downstairs — priced per month, in dollars.
30 labeled prompts across 10 categories. Prove the router agrees with humans before you trust it.