Muse Spark 1.2
Language modelPrevious generationCard summarizedMuse Spark 1.2 is optimized for real coding workflows, with higher first-attempt accuracy and more reliable tool calling.
Active (previous version; 1.3 recommended for new work)● Re-checked 12 Oct 2026 · 40 facts · 3 corrections · 1 unconfirmedSource: Introducing Muse Code and Muse Spark 1.2 (launch post) and evaluation methodology (no system card published)
Use it via API
Where to call it
- Meta Model API
muse-spark-1.2
Supports
- Image input
- PDF input
- Structured outputs
- Reasoning control
- Tool calling
- Web search
- Prompt caching
Good for
- Code generation, complex debugging and codebase understanding
- End-to-end developer workflows with Muse Code, which it was co-trained with
- Long-horizon coding: whole-repository generation, large projects and auto-research
Watch out for
Overview
Muse Spark 1.2
Muse Spark 1.2 is optimized for real coding workflows, with higher first-attempt accuracy and more reliable tool calling.
- Cost
- $1.25 in
- Context
- 1M
- Input / output
- $1.25 / $4.25
- Max output
- —
- Knows up to
- —
- Released
- 5 Aug 2026
A coding-focused update to Muse Spark 1.1, released with Meta's Muse Code terminal agent. Meta scaled up training compute on coding tasks, widened its training environments and co-trained the model with Muse Code. Meta has published no system card for 1.2; this summary uses the launch post, the multimodal follow-up post, the model page and the evaluation methodology. launch post
muse-spark-1.2- Input / output per 1M
- $1.25 / $4.25
- Context window
- 1M
- Max output
- —
- Knows up to
- —
- Reasoning
- Reasoning model; effort adjustable
- Weights
- Closed
About this card. A model card is the maker's own account of a model: what it's for, how it was trained and tested, and where it falls short. This page condenses Meta's Introducing Muse Code and Muse Spark 1.2 (launch post) and evaluation methodology (no system card published). Every claim carries its source page.