Safeguard: Zero

Overview

Safeguard's no-weights model: it reads a data question into a deterministic, replayable query in process, so nothing leaves the platform and no model tokens are used.

Provider

Safeguard

Modality

Text

Input

text

Output

text

Weights

Safeguard model

Tags

security, token-free, deterministic

Docs

About Zero

Data policy

Prompts go to

Nowhere: Zero runs in process on the Safeguard platform

Retention

No model provider is involved. 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 Zero can be deployed, bought and reached through Safeguard.

Deployment

Public cloudPrivate cloudOn-premAir-gapped

Procurement

Direct from Safeguard

Inference regions

Not published yet

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

Pricing

Notes

Zero uses no model tokens: deterministic analysis, no LLM consumption.

Source

Safeguard pricing , last verified October 8, 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/zero",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

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