Muse Glimmer

Price

Input

Price on request

Output

Price on request

Notes

Price on request: not served on Meta Model API (self-hosted only), no first-party per-token price.

Source

Meta pricing

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

Model

Context

128K (128,000 tokens)

Modality

Text and image

Input

text, image

Output

text

Weights

Open weights

Tags

open-weights, self-hosted, vision

Docs

Provider documentation

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

Policy

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

Base URL https://api.safeguard.sh/v1, model meta/muse-glimmer.