Self-host BitRouter

This is the production path for running BitRouter on your own infrastructure: a committed config file, real provider keys, the router running as a managed daemon, metrics export, and basic hardening. If you just want it running in 60 seconds, start with Installation — this guide picks up where that leaves off. Deciding between self-host and the hosted product? See Self-host vs Cloud.

The router listens on 127.0.0.1:4356 by default — loopback only, until you explicitly choose otherwise.

1. Generate and structure bitrouter.yaml

Scaffold a commented starter file:

bitrouter init                 # writes ./bitrouter.yaml
bitrouter init -c /etc/bitrouter/bitrouter.yaml

bitrouter init writes a starter config with skip_auth: true. Edit it to configure providers, routing, and the rest. Treat bitrouter.yaml as infrastructure-as-code: commit it, review changes, and keep secrets out of it (use ${VAR} references, resolved from the environment at load time).

The config is keyed into top-level sections — the ones you'll touch first are server, providers, and models:

# yaml-language-server: $schema=https://bitrouter.dev/schema/v<VERSION>/config.schema.json

server:
  # Loopback by default; set 0.0.0.0 only when you intend to expose the router
  # on all interfaces.
  listen: 127.0.0.1:4356
  log_level: info

providers:
  openai:
    api_base: https://api.openai.com/v1
    api_key: ${OPENAI_API_KEY}
    models:
      - id: gpt-4o

  anthropic:
    api_base: https://api.anthropic.com
    api_key: ${ANTHROPIC_API_KEY}
    # `api_protocol` is a glob-prefix pattern list: the head of each set is the
    # preferred outbound protocol.
    api_protocol:
      - "*": messages
    models:
      - id: claude-sonnet-4-6

# A virtual model that fails over from one provider to another in declared
# order (the default `priority` strategy).
models:
  smart:
    strategy: priority
    endpoints:
      - provider: anthropic
        service_id: claude-sonnet-4-6
      - provider: openai
        service_id: gpt-4o

Structure that matters:

• providers is a map keyed by provider id (openai, anthropic, …). Each entry takes api_base (upstream base URL), api_key (usually a ${VAR} reference), an optional api_protocol pattern list, and a models list whose entries each require an id.
• api_protocol selects the outbound wire protocol per provider — e.g. messages for Anthropic. Known values include chat_completions, messages, generate_content, and responses.
• models declares virtual models: named aliases with a strategy (default priority) and an ordered list of endpoints, each pointing at a provider + service_id. This is how you get failover.
• server carries listen, log_level, an optional skip_auth, and an optional control_socket path.

Validate before you ship:

bitrouter config validate -c bitrouter.yaml

2. Environment and keys

Secrets stay in the environment, never in the committed file. The ${VAR} placeholders in bitrouter.yaml are resolved at load time:

export OPENAI_API_KEY=sk-...
export ANTHROPIC_API_KEY=sk-ant-...

In production, deliver these through your process manager's environment (a systemd EnvironmentFile, a secrets mount, etc.) rather than a shell profile. When you rotate a key, you don't need to restart — bitrouter reload forwards any provider API keys present in the current environment to the running daemon, so export OPENAI_API_KEY=…; bitrouter reload takes effect immediately.

3. Run as a daemon

For production you want the router running detached and supervised. The daemon lifecycle commands (verified against the CLI reference):

bitrouter start        # spawn `serve` as a detached background daemon
bitrouter status       # pid, listen address, routable model count, socket path
bitrouter reload       # hot-reload config + routing table (also via SIGHUP)
bitrouter restart      # drain in-flight requests (up to 30s), then start fresh
bitrouter stop         # stop the daemon

• bitrouter serve runs the server in the foreground (logs to stdout) — this is what you point a systemd unit or container entrypoint at.
• bitrouter start spawns a detached daemon and refuses to start if one is already running. Logs default to bitrouter.log next to the config file.
• bitrouter reload hot-reloads config and the routing table without dropping connections.

All commands accept -c / --config <path>; the daemon-control commands (stop, reload, status) also accept --socket <path> to override the Unix control socket. Under a process supervisor, prefer bitrouter serve as the foreground entrypoint and let the supervisor handle restarts:

# /etc/systemd/system/bitrouter.service
[Service]
ExecStart=/usr/local/bin/bitrouter serve -c /etc/bitrouter/bitrouter.yaml
EnvironmentFile=/etc/bitrouter/bitrouter.env
Restart=on-failure

4. Expose metrics

BitRouter exports observability per request and to standard backends. Self-hosted metrics flow through two surfaces:

• A GET /metrics endpoint, served when a Prometheus-style metrics renderer is wired into the router (the observability plugin wires one). Point Prometheus at it like any scrape target.
• OTLP export of traces and metrics to any OpenTelemetry backend, provided by the bitrouter-observe plugin (OTLP/HTTP or OTLP/gRPC).

You can also query spend straight from the CLI without standing up a dashboard, and trace how a model name resolves before it hits an upstream:

bitrouter route gpt-4o     # print the full fallback chain for a model

See Observability for the full export and attribution model.

5. Basic hardening

• Bind deliberately. Keep listen: 127.0.0.1:4356 unless you have a reason to expose it. If you set 0.0.0.0, put a reverse proxy with TLS and auth in front.
• Don't ship skip_auth: true on any non-loopback deployment (see §2).
• Keep secrets in the environment. Only ${VAR} references belong in the committed bitrouter.yaml; the config redacts api_key in debug output.
• Validate in CI. Run bitrouter config validate -c bitrouter.yaml on every change, and pin the # yaml-language-server schema URL to your version.
• Add a content firewall with Guardrails to block or redact request/response content.
• Reload, don't restart, for config changes so in-flight requests aren't dropped.

Next steps