One alias in front of Fireworks AI.
Your application calls a Relays alias. Relays holds the Fireworks AI credential, applies the route policy, and hands back the provider response in the shape your SDK expects.
- Your application
Keeps the OpenAI-compatible request it already sends.
- Relays
Holds the key, picks the candidate, writes the receipt.
Fireworks AI
Receives the call on its own base URL.
- OpenAI-compatible
- Chat Completions
- Bring your own Fireworks API key
FIREWORKS_API_KEY https://api.fireworks.ai/inference/v1- Maintained Relays preset
Relays’ Fireworks AI preset keeps the provider key server-side and exposes the OpenAI-compatible Chat Completions contract through a public Relays alias.
What is measured, and what is not.
Availability comes from Fireworks AI. Latency, error rate, and cost per successful request come from your own traffic, so Relays leaves them empty until requests run.
Relays measurements
Models at the edge.
Model IDs sit behind a Relays alias, so a catalogue change at Fireworks AI never reaches your code.
Every route carries a policy.
A route is a list of candidates, a budget, and a record of what happened. You set all three before any traffic runs.
Candidates stay inside the contract.
Fireworks AI can be an explicit candidate or fallback in an eligible Chat Completions route.
See how a route is chosenA ceiling on this route.
Set an alert threshold and a stop threshold for the route rather than for the whole application. Relays checks both before the call goes upstream.
Each attempt is written down.
Every call records the alias, the candidates tried, the status each returned, tokens in and out, and the estimated cost of the attempt that served it.
Read a route receipt
One endpoint is enough to start.
Keep the client you already wrote. Bring us the workload and we will map the first Fireworks AI route with you.
