Skip to content

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
1.1 KB
Raw Blame
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0

# Local routes used by run_local_soak_test.py; no provider credentials are required.

schema_version = 1

[llm_clients.mock]
format = "openai_chat"
base_url = "http://127.0.0.1:8100/v1"
max_retries = 10

[targets.classifier]
id = "mock/classifier"
llm_client = "mock"

[targets.strong]
id = "mock/strong"
llm_client = "mock"

[targets.weak]
id = "mock/weak"
llm_client = "mock"

[routes.noop]
id = "switchyard/noop"
type = "noop"

[routes.random]
id = "switchyard/random"
type = "random"
targets = ["weak", "strong"]
weights = [1, 0]
seed = 42

[routes.passthrough]
id = "switchyard/passthrough"
type = "passthrough"
target = "weak"

[routes.classifier]
id = "switchyard/classifier"
type = "llm_classifier"
mode = "capability"
classifier_target = "classifier"
strong_target = "strong"
weak_target = "weak"
base_threshold = 1.0
max_output_tokens = 1

[routes.stage]
id = "switchyard/stage"
type = "stage_router"
capable_target = "strong"
efficient_target = "weak"
picker = "efficient_first"
confidence_threshold = 1.0