Safeguard
Griffin
safeguard/griffin
Request access
Not served yet. Ask for access and we will tell you when it is live.
Safeguard security model for remediation and reasoning: reachability, patch authoring and fix pull requests.
Price
- Input
- Price on request
- Output
- Price on request
- 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.
Model
- Context
- 128K (128,000 tokens)
- 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.
Call it with any OpenAI SDK
Available when the model is live
from openai import OpenAI
client = OpenAI(
base_url="https://api.safeguard.sh/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/v1, model safeguard/griffin.
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.