Microsoft Foundry Model Router: one deployment that picks the best LLM per request in real time
lee_stott · x · 2026-09-04
Ahead of his Agentcon London talk, Lee Stott shared docs on Microsoft Foundry's Model Router:
- A trained routing model that sends each prompt to the most suitable underlying LLM in real time
- Deploys like any Foundry model—one deployment balancing performance, cost, and latency
- Works as a drop-in deployment or an optimization layer, replacing manual hill-climbing model selection
- Microsoft still recommends evaluating against your baseline to confirm managed routing helps your workload
More from coding & agent
- GPT Sol plays real-time table tennis via latency-aware agent research loop — wzenus · 2026-10-21
- Daytona raises $60M Series B at $1B valuation to build the agent cloud — tsi_org · 2026-10-21
- PostgreSQL 19 slips to November as LLM-assisted code review floods committers with edge cases — sanjaykalra · 2026-10-21
- 9x Vision open-sources video perception for agents: timestamped evidence via MCP and CLI — koto9x · 2026-10-21
- LangChain adds Human-in-the-Loop beta to Managed Deep Agents — LangChain · 2026-10-21
- Voxtral 3 ships a LiveKit-based voice agent SDK streaming listen-think-speak — MistralAI · 2026-10-21