Gateway API
The metered, OpenAI-compatible LLM proxy — chat completions and embeddings, priced per model against a versioned PAX rate card and debited from a per-user credit ledger.
The gateway is an OpenAI-compatible LLM proxy that meters every call: it prices the request against a versioned rate card, debits a per-user PAX credit ledger, then forwards to the upstream provider.
Routes
| Method | Path | Purpose |
|---|---|---|
| GET | /healthz | Liveness. |
| POST | /v1/chat/completions | OpenAI-compatible chat completion (metered). |
| POST | /v1/embeddings | Embeddings (input-only pricing; metered). |
Metering model
The model id is looked up in the versioned rate card (RateTableVersion). PAX rates are derived from USD provider prices at a fixed PAX reference.
Free-tier callers are restricted to a per-slot model whitelist and a daily PAX cap. Other models require X-Matrix-BYO-API-Key.
Token usage is priced and written to the credit_ledger, recording the rate_table_v so historical rows replay byte-identically after a reprice.
Every ledger row records the rate-table version that priced it, so historical costs remain auditable and reproducible even after the rate card is bumped.
Chat completions
curl -X POST https://gateway.example/v1/chat/completions \
-H "Authorization: Bearer $MATRIX_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "accounts/fireworks/models/gpt-oss-120b",
"messages": [{"role": "user", "content": "Hello"}]
}'The response is the standard OpenAI chat-completion shape. Cost accounting happens server-side; inspect the credit ledger for the debited PAX amount and the rate_table_v used.