modelstatus.dev

InferenceNet

5 endpoints · 1 unhealthy · worst uptime 87.71%

  • Kimi K399.34%
    Healthy24h 97.80%
    7d
    95.19%
    30d
    95.19%
    p50
    2.29s
    p99
    39.5s
    Throughput
    24 tps
    Context
    1.0M
    $/Mtok
    $2.10 / $10.95
    inference-net/fp4fp4
  • GLM 5.397.09%
    Healthy24h 73.98%
    7d
    10.23%
    30d
    10.23%
    p50
    1.72s
    p99
    58.6s
    Throughput
    57 tps
    Context
    1.0M
    $/Mtok
    $0.900 / $3.00
    inference-net/fp4fp4
  • Down24h 96.48%
    7d
    96.62%
    30d
    96.62%
    p50
    2.87s
    p99
    34.9s
    Throughput
    17 tps
    Context
    1.0M
    $/Mtok
    $0.090 / $0.280
    inference-net/fp4fp4
  • No data24h 100%
    7d
    100%
    30d
    100%
    p50
    1.31s
    p99
    4.42s
    Throughput
    5.0 tps
    Context
    128K
    $/Mtok
    $0.050 / $0.230
    inference-net
  • No data24h 100%
    7d
    99.99%
    30d
    99.99%
    p50
    1.49s
    p99
    6.50s
    Throughput
    16 tps
    Context
    128K
    $/Mtok
    $0.030 / $0.150
    inference-net

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

Colour by hourly mean uptime:≥ 95%90–95%< 90%no data

Through the live last bucket (raw rounds, updated every collection round) · 5 endpoints with data, sorted worst-first.