Route to 25+ models from every major provider. Pay per token. Set hard spend limits. Never get locked in.
# same endpoint — swap the model string curl https://api.routerplex.com/v1/chat/completions \ -H "Authorization: Bearer $ROUTERPLEX_KEY" \ -d '{ "model": "claude-opus-4-8" }'
25+ models · 11 providers · one endpoint
§ 02 — Why RouterPlex
Every provider has its own SDK, pricing model, and quota system. RouterPlex collapses all of that into one account.
spend limits · scoped keys · per-key analytics · auto fallbacks — standard on every account
§ 03 — Pricing
… · prices in USD per 1M tokens, billed per token
§ 04 — How it works
No subscriptions, no minimums, no credit card to start.
Start now →Sign up with email or GitHub. You start with $5 in credit — no card, no subscription.
Create a key per project. Attach a hard budget, a model allowlist, or rate limits — spend stops the instant a cap is hit.
Keep your OpenAI client. Change the base URL, pick any model from the catalog, ship.
§ 05 — The deal
Every model is billed at the vendor's public list price, per token, from a prepaid balance you top up by card or crypto. 25+ chat and image models across 11 providers — and the meter only runs when you call one.
* Credit never expires. When your balance runs out, requests stop — they never overdraft.
§ 06 — Get started
$5 in free credits. No credit card required.
one key · every model · billed per token