Models / Meta
Muse Spark 1.3
by Meta ·
meta/muse-spark-1.3Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...
reasoningtool-usevisionreleased 2026-09-02
Legal score · raw
-
not yet benchmarked
Context
1.05M
max output 944K
Input
$1.56
per 1M tokens
Output
$5.31
per 1M tokens
Suite cost
-
no run recorded
Prompt caching
Grounded answers re-send the same retrieved authority every turn, so a cached read is what a long matter actually costs. Prices are per 1M tokens, from the provider’s own catalog.
Cache read
$0.19
8.3x cheaper than uncached
Uncached input
$1.56
per 1M tokens
Capabilities
Modalities
in textimagevideofile
out text
Request parameters it accepts
include_reasoningmax_tokensreasoningreasoning_effortrepetition_penaltyresponse_formatstructured_outputstemperaturetool_choicetoolstop_ktop_p
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.