by Meta AI

Muse Spark 1.2.

multimodal closed 1M ctx
Cheapest input
$1.25/M
on OpenRouter
Cheapest output
$4.25/M
on OpenRouter
Hosted equiv.
~$1.53/hr
@ 100 tok/s on OpenRouter

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...

Hosted API only

No self-host path — closed weights.

Muse Spark 1.2's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $1.25 $4.25 Launch ↗
Sources

Official references.

FAQ

Frequently asked.

How do I run Muse Spark 1.2?
Muse Spark 1.2 is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access Muse Spark 1.2?
Muse Spark 1.2 is available via OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Muse Spark 1.2?
API pricing starts at $1.25/M input tokens and $4.25/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Muse Spark 1.2 open-source or proprietary?
Muse Spark 1.2 is a proprietary model from Meta AI. Access is API-only — there are no public weights to download.