Safeguard: Eagle

Overview

Safeguard security model for discovery and triage: malicious package and typosquat classification, path ranking.

Provider

Safeguard

Modality

Text

Input

text

Output

text

Parameters

70B

Weights

Safeguard model

Tags

security, classification

Docs

About Eagle

Data policy

Prompts go to

Safeguard, on its own infrastructure

Retention

Customer data is never used to train shared models.

Zero data retention

Not stated by the provider

Region

The region your Safeguard workspace runs in

Policy

Safeguard data policy

Summarised from the provider's published terms. The provider's own policy is what applies.

Where you can run it

How Eagle can be deployed, bought and reached through Safeguard.

Deployment

Public cloudPrivate cloudOn-premAir-gapped

Procurement

Direct from Safeguard

Inference regions

Available in 245 countries and territories, on-prem and air-gapped.Not offered in Cuba, Iran, North Korea and Syria.Also not offered in the Crimea region of Ukraine or the so-called Donetsk People's Republic (DNR) and Luhansk People's Republic (LNR) regions of Ukraine.

On-prem and air-gapped deployments run wherever you install them.

Pricing

Source

Safeguard pricing , last verified October 9, 2026

Safeguard model, priced by Safeguard.

API

OpenAI-compatible. Your API key and access to this model are set up for your workspace when you choose Use with Safeguard.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.safeguard.sh/gpt/v1",
    api_key="SAFEGUARD_API_KEY",
)

response = client.chat.completions.create(
    model="safeguard/eagle",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Base URL https://api.safeguard.sh/gpt/v1, model safeguard/eagle.

Eagle is not callable through the API yet. This request works once Safeguard opens it and switches the gateway on for your workspace.