Muse Spark Open

meta/muse-spark-open

open-weight Muse Spark for coding and agentic workflows.

cmd --model meta/muse-spark-open
Intelligence index
not yet scored
Coding index
not yet scored
Input
$1.25 /M
Output
$4.25 /M
Cache read
$0.15 /M
Agent-loop cost
$0.48 /M in
Context window
1.05M tokens
Released
October 15, 2026
Modalities
→

vs. the lineup

Muse Spark Open beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.

pin a rival:
ModelIntelligenceCodingInput $/MOutput $/MBlended $/MContext
Muse Spark 1.348.1◆75.8◆$1.25$4.25$21.05M◆
Muse Spark 1.239.672.2$1.25$4.25$21.05M◆
Muse Spark 1.133.771.3$1.25$4.25$21.05M◆
Muse Spark Open ◆——$1.25$4.25$21.05M◆
Muse Spark 1.2 Contributor——$0.10◆$0.20◆$0.13◆1.05M◆
Muse Spark 1.3 Contributor——$0.10◆$0.20◆$0.13◆1.05M◆
DeepSeek V4 Pro (latest)pinned3668.8$0.66$1.98$0.991M
DeepSeek V4 Flash (latest)pinned3469.1$0.15$0.60$0.261M

usage calculator

How far a month of credits goes on Muse Spark Open.

Input tokensfresh prompt
800
Output tokensmodel reply
180
Cache read tokensre-read context
50K
cost / request $0.0093 · in $1.25 · out $4.25 · cache $0.15 per M
fresh input 11%output 8%cache reads 81%
Requests / 30 days
648
$6 credits ÷ $0.0093 per request
~130 quick fixes~26 bug fixes~4 feature PRs

what real work costs

Real coding tasks priced end to end on Muse Spark Open, from a quick lookup to a full-repo agent run.

One agent task
$0.13
180K in at 75% cache hit, 12K out
What you pay
$0.66 /M
all-in across every token that task touched
Sticker input
$1.25 /M
cache reads bill at $0.15 /M instead
TaskTokens in · outMuse Spark OpenMiMo V2.6 ProClaude Haiku 4.5
Quick lookup / one-liner8K · 1K$0.0063$0.0012$0.0065
Review a 500-line PR60K · 4K$0.05$0.01$0.04
Fix a bug (agent loop)180K · 12K$0.13$0.03$0.12
Refactor a module320K · 20K$0.23$0.06$0.21
Full-repo agent run900K · 45K$0.54$0.13$0.49

frequently asked

How much does Muse Spark Open cost?
$1.25/M input and $4.25/M output, cache reads $0.15/M. In an agent loop most input is cache-read, so the effective input rate is about $0.48/M.
Which plan do I need?
Available on Go and above.
How do I switch to it?
Run cmd --model meta/muse-spark-open, or type /model in a session and pick it. You can switch mid-session without losing context.

Ship code that matches your taste

Command Code is the AI coding agent that continuously learns your taste. Start for $1.

Benchmarks from Artificial Analysis (v4.3)commandcode.ai/models/muse-spark-open