OpenRouter Launches Armor Beta: Uses Jev Model to Block Out-of-Policy Tool Calls with Lower Cost Than Claude Code

1 reports archived1 independent sourcesupdated 10/16/2026, 05:00:20

Synthesis & Latest Updates

1 Sources Cross-Validated

OpenRouter has launched Armor in beta, a security gateway that intercepts out-of-policy tool calls before agent execution. Leveraging TypesafeAI's Jev classification model, it claims superior detection performance compared to Claude Code's auto-classifier at a fraction of the cost, addressing the limitations of traditional regex-based filtering.

LATEST/OpenRouter has launched Armor in beta, a security gateway that intercepts out-of-policy tool calls before agent execution. Leveraging TypesafeAI's Jev classification model, it claims superior detection performance compared to Claude Code's auto-classifier at a fraction of the cost, addressing the limitations of traditional regex-based filtering.

HEAT TRENDHourly heat curve

3 fully observed hours

Now

27.8

Peak

29.206:00

24h change

–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

TIMELINECoverage timeline

Total 1 reports · Latest first

OpenRouter (@OpenRouter)T1·Oct 16, 05:0068 pts
OpenRouter Launches Armor Beta: Uses Jev Model to Block Out-of-Policy Tool Calls with Lower Cost Than Claude Code
- Armor uses a specialized small model (Jev) instead of regex or LLM self-checks to filter dangerous tool calls
- Claims better performance than Claude Code's auto-classifier at significantly lower cost
- Currently in Beta, targeting AI agent scenarios requiring high-security tool invocation
View Related Reports & Analysis Original Source