/ llm-router · v0.1
One API.
Every provider.
Zero lock-in.
An OpenAI-compatible inference API that routes every call to the right model. Switch providers without rewriting code, and see exactly what each request costs — all from a single dashboard.
No credit card. Free for evaluation.
/ what you get
One gateway. Four jobs.
For teams that ship LLM features and want one place to see what they cost.
OpenAI-compatible
Drop in for the OpenAI SDK or any HTTP client. Existing tools, frameworks, and integrations work without changes.
Multiple models, one endpoint
Switch between models by name. The router handles selection, retries, and fallback so your application code stays the same.
Usage & cost tracking
See exactly what each call costs in real time. Latency, error rate, and cache hits broken down per model.
Granular cost visibility
Per-model and per-user breakdowns of cost, latency, and errors. Cached prompts are tracked separately so you know what your spend actually buys.
/ how it works
From signup to insight in three steps.
No infrastructure to manage. Sign up, get a key, and start calling the API. Your dashboard tracks every call from there.
- 01Sign up
Create your account
Register with an email and password. No credit card required to start. Your dashboard and API key are ready in seconds.
- 02Route
Call one endpoint
A single OpenAI-compatible URL handles every model. Pick a model by name in the request body — no SDK changes needed.
- 03Observe
Track every call
Watch cost, latency, and error rate fill in live as your application makes calls. Filter by model, user, or time window.
/ get started
Ready to ship
your first call?
Create an account, generate an API key, and point your OpenAI SDK at https://api.llm.jmsystem.co.kr. Your dashboard tracks every call from the first request onward.