Safeguard: Griffin

Overview

Safeguard security model for remediation and reasoning: reachability, patch authoring and fix pull requests.

Provider

Safeguard

Modality

Text

Input

text

Output

text

Weights

Safeguard model

Tags

security, reasoning, coding

Docs

About Griffin

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 Griffin 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

Price on request: Safeguard has not published a per-token API rate for this model yet.

Source

No per-token list price is published

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/griffin",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

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