Models

AI Models

RedCell runs on a curated catalog of models specifically benchmarked and tuned for defensive security, code audit, and threat hunting tasks.

Available Catalog

Model IDContextReasoningBest For
glm-5.2default
GLM 5.2
200Klow · medium · highGeneral defensive-security reasoning.
hunter-r1
Hunter R1
128Kmedium · highThreat hunting & reverse-engineering investigations.

Reasoning Effort Settings

You can adjust how deeply the model thinks before producing a final turn or executing tool calls:

  • low — Fastest response time, suitable for straightforward code syntax lookups or simple log parsing.
  • medium — Balanced reasoning budget for code security reviews and general incident analysis (Default).
  • high — Maximum deep thinking cycles for complex threat hunting, malware behavior analysis, and multi-file code auditing.

Switching Models per Execution

Pass the --model flag to select a model for a specific command run:

redcell exec --model
redcell exec --model hunter-r1 "Analyze telemetry dump in ./logs"
Using model: hunter-r1 (128K context)...