Muse Spark 1.1

Muse Spark 1.1 is strongest at agentic performance, tool use, and computer use. It does well on long-running tasks with 1M token context window, can delegate execution to sub-agents running in parallel, and is trained to use computer interfaces on desktop, mobile, or browser.

Model overview

Model ID: meta/muse-spark-1.1
Provider: meta
Type: language
Context window: 1,048,576 tokens
Max output tokens: 1,048,576

Tags: reasoning, tool-use, implicit-caching

Model pricing

Metric	Value
`Input tokens (/1M)`	`$1.25`
`Output tokens (/1M)`	`$4.25`
`Image generation`	`n/a`
`Cached input read (/1M)`	`$0.15`
`Cached input write (/1M)`	`n/a`
`Pricing source`	`gateway`

Related docs

Model catalog

Browse every generated model page.

Open catalog

Pricing matrix

Compare model pricing across the full catalog.

Open pricing matrix