Muse Spark 1.3

Price

Input

$1.25 per 1M tokens

Output

$4.25 per 1M tokens

Notes

Standard tier (no training on your data). Cached input $0.15. No long-context premium. Contributor tier (muse-spark-1.3-contributor) is $0.10 / $0.20 in exchange for allowing training. Audio input not fully supported on 1.3.

Source

Meta pricing , last verified October 8, 2026

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

Model

Context

1.05M (1,048,576 tokens)

Modality

Text and image

Input

text, image, video, audio, file

Output

text

Weights

Closed

Tags

coding, agents, multimodal, long-context

Docs

Provider documentation

Data policy

Prompts go to

Meta (Meta Model API)

Retention

Standard tier: prompts and completions not used to train Meta models, Contributor tier allows training in exchange for lower prices. No retention period published in the API docs

Zero data retention

Not stated by the provider

Region

Not stated

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-spark-1.3",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Base URL https://api.safeguard.sh/v1, model meta/muse-spark-1.3.