Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.
Rust
docs(changelog): fix broken Metrics Reference link (#432)
LeonSGP76a19d4c3f5a
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex de81bbc1d..8324591d8 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -185,7 +185,7 @@ traffic that sits between client applications and LLM backends.`--list-models`), and `verify` / `launch --smoke` round-trip checks.- **Observability** — Prometheus `/metrics`, a JSON `/v1/stats`(`/v1/routing/stats` alias), and per-request cost/token/latency stats. See- [Metrics Reference](docs/METRICS_REFERENCE.md).+ [Metrics Reference](docs/internal/metrics_reference.md).- **Python library** — `SwitchyardRecipes` (`passthrough_recipe`,`random_routing_recipe`, `cascade_recipe`, `deterministic_routing_recipe`,…) and typed `ChatRequest` / `ChatResponse` containers for in-process use.