Decision Models for agentic security open sourced, free on OpenRouter
Open weights aimed at a niche most security teams have not tooling for yet: auditing agent sessions at full scale rather than sampling. Security and platform engineers operating multi-agent deployments can self-host under Apache or use the free OpenRouter window until 19 Nov to evaluate it against manual rule review. The Perplexity figure of 1 billion tokens and 14 rule fixes in a day gives a concrete benchmark for what such audit loops can yield.
OpenRouter CEO Alex Atallah highlighted "Decision Models," models built for agentic security that can process billions of tokens of telemetry, identify security issues, and help patch fixes at a scale and cost structure not previously possible. The models have been open sourced under Apache licenses and are free on OpenRouter until 19 Nov.
A concrete example shows how Perplexity used the Decider model internally: in one day it read 1 billion tokens across 7,000 agent sessions and surfaced flaws that led to 14 fixes to the company's agent security rules. The workflow moves beyond sampling-based log review, instead scanning the full record of agent behaviour to flag risky patterns.
The release signals a shift from manually written security rules toward model-assisted auditing of agent fleets. Teams running large numbers of autonomous agent sessions can now run full-telemetry review on their own logs, and the Apache licence means the models can be self-hosted or fine-tuned for internal policy enforcement.
Decision Models are the future of agentic security. They can process billions of tokens of telemetry, identify security issues, and help you patch fixes at a scale and cost structure not possible before. We’ve open sourced our models and made it free on Openrouter for a week. Alex Atallah @alexatallah Neat example of how Perplexity used Decider internally In one day it read 1B tokens across 7,000 agent sessions and found flaws that led to 14 fixes to their agent security rules. Both models are Apache-licensed and free on OpenRouter until Nov 19 🔗 View Quoted Tweet📊 19 ⚡
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Decision Models, OpenRouter, Perplexity, agents.
Source attribution: curated from Aravind Srinivas (@AravSrinivas).
