# Goodfire launches cheap inside‑out AI monitors

> The new probes watch a model’s internal signals, costing $51 for 1,500 sessions versus $233 for cheaper alternatives.

Oossa · 2026-10-08 · https://oossa.com/en/goodfire-launches-cheap-inside-out-ai-monitors

Goodfire, a startup that studies how AI models work, released an "inside‑out" monitor on Thursday, Oct 8, 2026. The probes read a model’s internal activations instead of re‑processing its outputs. Baseten customers can pick which risks to watch and what automated response to take. In Goodfire’s own test on the open model Kimi K3, 1,500 sessions cost about $51 and caught 94% of malicious hacking attempts.

## The facts

- Launch date: Oct 8, 2026 – "launched a cheaper option on Thursday"
- Cost: $51 for 1,500 sessions, versus $233 for a cheaper alternative

## Why it matters

Developers using open models can add low‑cost safety checks without large performance hits.

## Sources & references

1. [Goodfire says its new ‘inside-out’ monitors catch rogue AI agents at a fraction of the cost](https://techcrunch.com/2026/10/08/goodfire-says-its-new-inside-out-monitors-catch-rogue-ai-agents-at-a-fraction-of-the-cost/) – TechCrunch, 2026-10-08

Last updated: 2026-10-08