Route coding agent requests to the right model on Amazon Bedrock with NVIDIA NeMo Switchyard

What happened

Route coding agent requests to the right model on Amazon Bedrock with NVIDIA NeMo Switchyard, AWS Machine Learning Blog announced. Coding agents work in tasks, and the number that matters is cost per solved task, not price per token. Coding agents such as Claude Code and OpenAI Codex CLI (a text interface where commands are typed rather than clicked) work in tasks. NVIDIA is a semiconductor company based in Santa Clara.

A developer asks for a change, and the agent reads files, edits code, and runs tests until the work is done. One task can take a few model calls or dozens.

What the developer pays for is the task, not one call. The total depends on how many turns a model needs, how much history each turn replays, and how often a task has to be retried or never finishes.

Artificial Intelligence Coding agents such as Claude Code and OpenAI Codex CLI work in tasks. You pay for every attempt, including attempts on tasks that never finish.

So when you route a coding agent’s requests between models, judge the routing by cost per solved task: the total cost of your runs divided by the number of runs whose tests pass. NVIDIA NeMo Switchyard is an open source library that helps an AI agent (AI that carries out multi-step tasks rather than answering one question) choose which model handles each request. You define the models that it can use and the strategy that it follows.