modelstatus.dev

Muse Spark Open

meta/muse-spark-openInputOutput

Compare its 5 providers Incident RSSCompare with Muse Glimmer 30B, Muse Spark 1.1, Muse Spark 1.2

CompareMuse Spark Open

	State
BaseTenbaseten/fp4fp4	Healthy	100%	100%	100%	100%	519ms	2.59s	227 tps	1.0M	$1.25 / $4.25
Fireworksfireworks	Degraded	100%	86.27%	88.77%	88.77%	866ms	53.8s	44 tps	1.0M	$1.25 / $4.25
Modalmodal	Healthy	100%	100%	—	—	1.13s	13.3s	87 tps	1.0M	$1.25 / $4.25
Nebiusnebius/fp4fp4	Healthy	100%	87.98%	100%	100%	1.53s	8.28s	96 tps	1.0M	$1.25 / $4.25
Togethertogether	Healthy	100%	94.18%	98.95%	98.95%	559ms	100s	67 tps	1.0M	$1.25 / $4.25

BaseTen100%
Healthy24h 100%
7d
100%
30d
100%
p50
519ms
p99
2.59s
Throughput
227 tps
Context
1.0M
$/Mtok
$1.25 / $4.25
baseten/fp4fp4
Fireworks100%
Degraded24h 86.27%
7d
88.77%
30d
88.77%
p50
866ms
p99
53.8s
Throughput
44 tps
Context
1.0M
$/Mtok
$1.25 / $4.25
fireworks
Modal100%
Healthy24h 100%
7d
—
30d
—
p50
1.13s
p99
13.3s
Throughput
87 tps
Context
1.0M
$/Mtok
$1.25 / $4.25
modal
Nebius100%
Healthy24h 87.98%
7d
100%
30d
100%
p50
1.53s
p99
8.28s
Throughput
96 tps
Context
1.0M
$/Mtok
$1.25 / $4.25
nebius/fp4fp4
Together100%
Healthy24h 94.18%
7d
98.95%
30d
98.95%
p50
559ms
p99
100s
Throughput
67 tps
Context
1.0M
$/Mtok
$1.25 / $4.25
together

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

Availability

Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.

Time to first token

Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.

Daily availability

One row per endpoint · one dot per day · last 90 days.

Jul

Aug

Sep

Oct

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 5 endpoints · 1 day with data, 2 endpoint-days below 90%.