Safeguard
Meta logo

Meta: Llama 4 Scout

meta/llama-4-scoutAvailable via Safeguard
Private cloudOn-prem

Use with Safeguard

Llama 4 Scout is available via Safeguard. Leave your work email and we will enable it for your workspace.

We will also add you to our newsletter; unsubscribe any time.

Released
April 5, 2025
Context
10,000,000 tokens
Input
Price on request
Output
Price on request

Overview

Open-weight Llama 4 MoE model (17B active, 109B total, 16 experts) with text and image input and a 10M-token context.

Provider
Meta logoMeta
Modality
Text and image
Input
text, image
Output
text
Weights
Open weights
Supported parameters
toolsProvider's model page, checked .
Distillable
Conditional (licence terms)Llama 4 Community License: a model trained on its outputs that is distributed must start its name with "Llama" and show "Built with Llama". The licence's other terms apply.Licence or terms, checked .
Tags
open-weights, multimodal, long-context

Data policy

Prompts go to
Wherever you or your chosen host run the weights (no Meta-hosted API for this model)
Retention
Set by the host, Meta does not receive prompts when you self-host
Zero data retention
Not stated by the provider
Region
Depends on host

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

Where you can run it

How Llama 4 Scout can be deployed, bought and reached through Safeguard.

Deployment
Private cloudOn-prem
Procurement
Not published yet
Inference regions
Not published yet

On-prem deployments run wherever you install them.

Pricing

ProviderInput / 1M tokensOutput / 1M tokensContext
MetaPrice on requestPrice on request10M
Notes
Price on request: Meta publishes no first-party USD per-token price for Llama models.

No markup on model usage: you pay the provider's list price.

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="meta/llama-4-scout",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Base URL https://api.safeguard.sh/gpt/v1, model meta/llama-4-scout.

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.