The whole dayFri 6 Nov 2026
AI Compass
ArchiveAbout

OpenRouter launches next-generation Auto Router and Auto Code for coding agents

The new routers pick a model and reasoning effort per request within workspace guardrails, matching Claude Opus 5.5 on coding benchmarks at 74% lower cost.

Purple branching pathways routing requests from circular nodes to target model endpoints.
Image: OpenRouter

OpenRouter launched its next-generation Auto Router (openrouter/auto) alongside a dedicated coding router, Auto Code (openrouter/auto-code), on 6 November 2026. Processing more than 2.5T tokens per month, the updated routing engine evaluates each incoming prompt to select both the target model and the reasoning effort level from the pool permitted by the caller’s zero data retention (ZDR), provider, and bring-your-own-key policies.

Auto Code scores 74.3% on Deep SWE and 62.5% on SWE-Atlas QA, outperforming the previous Auto Router across five benchmarks.
Auto Router and Auto Code accuracy and cost per task compared with the previous Auto Router.Image: OpenRouter

Auto Code is tuned specifically for multi-turn software engineering and agentic tool use, achieving 74.3% on Deep SWE at $1.98 per task and cutting cost per task by roughly 74% compared with single frontier model calls at comparable accuracy. Both routers operate with a p90 routing decision latency of 0.65 seconds and expose per-request routing rationale and candidate model selection shares in the OpenRouter chat interface.

OpenRouter chat sidebar showing per-request routing insights, task complexity, and candidate model selection shares.
Per-request routing insights display the chosen model, task classification, and candidate selection breakdown.Image: OpenRouter

Sources

  1. PrimaryIntroducing the New Auto and Auto Code Routersopenrouter.ai · OpenRouter announcement
  2. On XOpenRouter next-generation routers postx.com · Official X announcement

The rest of the day

Read the whole day

Spotted an error? Email aiforsuccess.in+compass@gmail.com or tag @ai_for_success on X