Skip to main content
Antares
Compact tier
Tool calling

Antares 1B (Security)

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

by Cisco

Antares group

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.

Antares 1B (Security) trains on your agent's own traces with LoRA adapters or full finetuning, is benchmarked against your production model before any traffic moves, and serves through the same OpenAI-compatible API as every Overmind model. The final weights are yours to download and run anywhere.

Good for

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

More in Antares

← Back to all models
Train now

Specs & cost

Cost to trainfrom $0.55
Cost to run (1M tok)from $4.00
GroupAntares
FamilyCisco
Parameters1.8B
TierCompact
Context window128K
Max training context128K
Tool callingYes
Methods—
Train now
Training docs

On Overmind

  1. 01 Train on your data

    LoRA or full finetuning on a training-intent dataset from your agent's traces. Overmind recommends tiers from your data stats; you can edit every setting.

  2. 02 Benchmark vs production

    Each finished model is scored on your eval set with your rubric against the model your agent runs today. The headline is the baseline delta per metric.

  3. 03 Serve and own the weights

    Succeeded runs deploy automatically to Inference through the same OpenAI-compatible API. The final weights are yours to download and run anywhere.