Code with Muse Spark 1.2
in AdaL
Meta's latest agentic coding checkpoint. Use muse-spark-1.2 in AdaL for long-running code, debug, and refactor work with a 1M-token context window.
Get StartedRun /model and pick Muse Spark 1.2 · $1.25/M input · $4.25/M output
Why use Muse Spark 1.2 in AdaL
Key capabilities and pricing
Latest agentic coding checkpoint
Meta's newest Muse Spark release, tuned for code generation, debugging, and long-running developer workflows.
1M context window
1,048,576-token input budget for whole-repository sessions.
128K max output
Room for large multi-file refactors in a single response.
Configurable reasoning effort
Thinking model with effort levels you set per task for speed/quality tradeoffs.
Vision support
Reads screenshots, diagrams, and other visual context alongside code.
$1.25/M input · $4.25/M output
Cached input at $0.15/M cuts the cost of repeated context.
How to pick Muse Spark 1.2
Available in AdaL CLI and Desktop through the model selector
Open AdaL CLI or AdaL Desktop
Use the coding environment where AdaL already understands your repo, tools, and task context.
Run /model
Open the model selector and choose your model from the list.
Start your task
Ask AdaL to inspect, plan, edit, test, and review with your chosen model powering the agent loop.
What to know
Key details about Muse Spark 1.2
"Muse Spark 1.2 is positioned as the latest agentic coding checkpoint in the Muse Spark family."
Meta
"Use Muse Spark 1.2 for large, long-running coding tasks — a 1M context and 128K output in one session."
AdaL
"$1.25/M input, $4.25/M output, $0.15/M cached — the same Standard-tier pricing as Muse Spark 1.1."
Pricing
"Available now in AdaL CLI and Desktop."
Availability
Ready to try Muse Spark 1.2 in AdaL?
Open AdaL CLI or Desktop, run /model, and choose Muse Spark 1.2.
Get Started with AdaL