# Antares 350M (Security)

> Canonical: https://www.overmindlab.ai/models/antares-350m

Security-specialised 350M base for high-frequency vulnerability jobs.

| Property | Value |
| --- | --- |
| Model ID | fdtn-ai/antares-350m |
| Provider | Cisco |
| Group | Antares |
| Parameters | 350M |
| Tier | Compact |
| Context window | 32K |
| Max training context | 32K |
| Tool calling | Yes |
| Training methods | — |
| Training cost | from $0.50 |
| Serving cost (per 1M output tokens) | from $2.50 |

## Overview

Antares models are security-specialised compact bases, trained for vulnerability localisation. They stay small enough to serve cheaply at volume when the job is narrow and high-frequency, and they train like every other catalogue model on Overmind.

Security-specialised compact models, trained for vulnerability localisation. Small enough to serve cheaply at volume on a narrow, high-frequency job.

## Good for

- Vulnerability localisation and triage
- Narrow, high-frequency security jobs
- Cheap serving after domain training

Train this model on your agent's data: https://docs.overmindlab.ai/models/training.md

## Related models

- [Antares 1B (Security)](https://www.overmindlab.ai/models/antares-1b): 1.8B, 128K context