OpenRouter unveils Auto Router & Auto Code: Opus 5.5-level coding at 74% less cost
AccBalanced · x · 2026-11-07
OpenRouter has launched its next-generation model routers: Auto Router for general Q&A and agents, and Auto Code for coding agents.
- Auto Code benchmarks similarly to Opus 5.5 while costing 74% less, with a p90 latency of just 0.65s
- The router is cache-aware: switching models incurs extra cost as the input token cache is rebuilt, so Auto Router prefers adjusting reasoning effort when that suffices, switching models only when the gain justifies the cache loss
- When it does switch, it weighs live prices, benchmark performance, user-defined guardrails, and more to pick both the model and the reasoning effort
- Routing decisions are shown per request
More from coding & agent
- Dev designs a cybersecurity agent that remembers past attacks with Hindsight — Adventurous-Ant-9370 · 2026-11-07
- Solo dev: most bad LLM coach answers traced to my context, not the model — Aksel_010 · 2026-11-07
- New blog: how your RL judge and credit assignment shape model reasoning quality — tokenbender · 2026-11-07
- Enzyme open-sources a personal agent memory layer saving 40% tokens vs grep — _AustinCalvert_ · 2026-11-07
- Qoder lands stealth model 'Qoduck', free daily for individual users for limited time — hey_abusiddik · 2026-11-07
- Agent autonomy should be earned in stages, not assumed, argues dev — Few-Garlic2725 · 2026-11-07