modelstatus.dev

Muse Glimmer 30B

meta/muse-glimmer-30b

Compare with Muse Spark 1.2, Muse Spark 1.1, GLM 5.2

CompareMuse Glimmer 30B
  • DeepInfra100%
    Healthy24h 99.84%
    p50
    198ms
    p99
    2.13s
    Throughput
    131 tps
    Context
    131K
    $/Mtok
    $0.300 / $1.20
    deepinfra/bf16bf16
  • Fireworks100%
    Healthy24h 99.97%
    p50
    215ms
    p99
    885ms
    Throughput
    58 tps
    Context
    131K
    $/Mtok
    $0.350 / $1.50
    fireworks
  • Parasail100%
    Healthy24h 99.94%
    p50
    1.53s
    p99
    4.81s
    Throughput
    38 tps
    Context
    131K
    $/Mtok
    $0.300 / $1.10
    parasail/bf16bf16
  • Together99.26%
    Healthy24h 99.90%
    p50
    1.58s
    p99
    6.29s
    Throughput
    75 tps
    Context
    131K
    $/Mtok
    $0.350 / $1.50
    together
  • Phala98.57%
    Healthy24h 99.87%
    p50
    1.04s
    p99
    4.14s
    Throughput
    42 tps
    Context
    131K
    $/Mtok
    $0.300 / $1.10
    phala

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

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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.

Throughput

Median tokens per second.