Muse AI · Released Mar 15, 2026
Muse Spark 1.2 (xhigh)
High-efficiency reasoning model tuned for rapid agentic dispatch, low per-task overhead, and creative problem solving.
OpenRating Index
56.9
0–100 composite
Reasoning Index
78.2
0–100 composite
Cost / Task
$0.40
benchmark run
Output speed
98 tok/s
blended tok/s
Time to first token
0.6s
median latency
Input price
$0.35
per 1M tokens
Output price
$1.4
per 1M tokens
Context window
128K
tokens
Strengths
Sub-$0.41 task cost with high intelligence index score
Fast response initiation and low token latency
Optimized for multi-agent dispatch pipelines
How we rate Muse Spark 1.2 (xhigh)
OpenRating scores every model on the same axes. The OpenRating Index is a weighted composite of reasoning, knowledge, and agentic benchmarks, normalised to a 0–100 scale. Speed is blended output measured in tokens per second under standardised load, with time-to-first-token reported separately. Prices are list input and output prices per million tokens, and Task Cost measures end-to-end workload spending.
OpenRating Index
56.9
Reasoning Index
78.2
Token Pricing
Input per 1M tokens
$0.35
Output per 1M tokens
$1.4
Cost of 1M input + 1M output
$1.75
Task Cost Economics
Empirical cost breakdown for a standard OpenRating Index benchmark task ($0.40 total).
Related models
Compare Muse Spark 1.2 (xhigh) with the models it is most often measured against.