# Antares 1B (Security)

> Canonical: https://www.overmindlab.ai/models/antares-1b

Security-specialised ~1.8B Antares with 128K inference context.

| Property | Value |
| --- | --- |
| Model ID | fdtn-ai/antares-1b |
| Provider | Cisco |
| Group | Antares |
| Parameters | 1.8B |
| Tier | Compact |
| Context window | 128K |
| Max training context | 128K |
| Tool calling | Yes |
| Training methods | — |
| Training cost | from $0.55 |
| Serving cost (per 1M output tokens) | from $4.00 |

## 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 350M (Security)](https://www.overmindlab.ai/models/antares-350m): 350M, 32K context