Opus 5.5’s biggest tell is the word “dependable,” which pops up 23 times more often than in human samples.
Read the original at TechCrunch AI: Opus 5.5 loves to tell you ‘this matters’ (and other AI writing tells)
How OpenSmartRoute helps
Teams using OpenSmartRoute gain immediate clarity on why Opus 5.5 overuses the word "dependable." The router scores every candidate model on quality, cost, speed, and safety before sending a request. This scoring lets a team set weights per request to match specific business needs.
The platform keeps a models catalogue with prices and public rankings built from real traffic. When Opus 5.5 appears in this catalogue, the team sees its cost compared to other options. A savings ledger shows what each routed request cost next to what the most expensive model would have cost.
Input guard spots prompt injection and personal data before a request leaves the system. If the team wants to limit Opus 5.5 use, hard rules pin requests with personal data to on-premises models. The 'osr eval' tool measures routing accuracy on the team's own prompts and can fail a build when it drops. A new model is one catalogue entry and competes on the next request without changing the app.