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
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
# Service name from Dynamo's kube-prometheus-stack setup.
endpoint = "http://prometheus-kube-prometheus-prometheus.monitoring.svc.cluster.local:9090/api/v1/query"
poll_interval_ms = 1000
timeout_ms = 500
# Replace these with labels selecting every engine in the pool, without duplicate series.
[[models]]
model = "Qwen/Qwen3-0.6B"
selector = 'namespace="switchyard", model_name="Qwen/Qwen3-0.6B", endpoint="system"'
[[models]]
model = "Qwen/Qwen3-1.7B"
selector = 'namespace="switchyard", model_name="Qwen/Qwen3-1.7B", endpoint="system"'