One alias in front of Anthropic.
Your application calls a Relays alias. Relays holds the Anthropic credential, applies the route policy, and hands back the provider response in the shape your SDK expects.
- Your application
Keeps the Anthropic request it already sends.
- Relays
Holds the key, picks the candidate, writes the receipt.
- Anthropic
Receives the call on its own base URL.
- Anthropic
- Messages
- Bring your own Anthropic API key
ANTHROPIC_API_KEY https://api.anthropic.com/v1- Registry entry
Relays exposes the native Messages edge, including streaming, thinking, tool payloads, and MCP configuration where the selected route can honor the request.
What is measured, and what is not.
Availability comes from Anthropic. 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 Anthropic 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.
Messages routes can fall back only to configured Anthropic-compatible candidates that satisfy the requested capabilities. Relays does not flatten Messages into Chat Completions for cross-protocol fallback.
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 Anthropic route with you.
