# Meta's Muse Spark Open is out: 816B open weights, $1.25/$4.25 on API hosts, and a two-Mac Studio local run

> Meta released Muse Spark Open weights: 816B total, 42B active, 1M context, multimodal. OpenRouter hosts list $1.25/$4.25 per million. Local runs need the model card's hardware, or two M5 Ultra Mac Studios.

Published 2026-10-15T08:00:00-07:00 · Model & Plan Comparisons · Canonical: https://news.littlewolflabs.com/posts/2026-10-15-muse-spark-open

Meta released Muse Spark Open, an open-weights model with 816 billion total parameters, 42 billion active, and a 1 million token context. [Meta's post](https://research.meta.ai/blog/muse-spark-open) calls it natively multimodal. [AI at Meta](https://x.com/AIatMeta/status/2110779754274292212) lists text, image, video, and audio. Weights are on [Hugging Face](https://huggingface.co/collections/meta-models/muse-spark-open) in BF16 and NVFP4. The [BF16 model card](https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B) says a local GPU needs at least 700GB of VRAM for NVFP4 and 2TB for BF16.

Meta says two Apple M5 Ultra Mac Studios, via MLX, hold the model. [Mark Zuckerberg](https://x.com/finkd/status/2110778025629347999) posted that it runs on the new Mac Studios with Apple's John Ternus. Meta's own demos, using Muse Code on the open model, ship iOS changes to Ice Cubes and drive DaVinci Resolve end to end. Those are Meta's demos.

The hosted rate is on the [pricing table](/pricing-limits).

## What it costs

[OpenRouter](https://openrouter.ai/meta/muse-spark-open) lists $1.25 per million input tokens and $4.25 per million output. Its table shows that rate at Together, Nebius, Baseten, and Fireworks. Cache read is $0.15 per million on Together, Baseten, and Fireworks. Nebius does not print a cache price. Meta's post also names Groq and Modal as hosts.

Muse Wonder on Meta's own Model API is $4 input and $20 output. Claude Opus 5.5 is $4 and $20. Those are the published API stickers, not this model's.

The [Muse Model License](https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B) on the model card allows free commercial use if the product displays "Built with Muse Spark Open." A model-as-a-service seller whose gross revenue, with affiliates, exceeds $20 million in any twelve months has to make a separate deal with Meta before offering the model.

## Should you switch

Try the hosted API if you want a Muse-class coding agent without Muse Code's $50 Power or $200 Maximum plan. Run it locally only if you have the card's GPUs or two M5 Ultra Mac Studios. Keep Claude or Grok for daily work until someone other than Meta publishes benches.