modelstatus.dev

GLM 5.1

z-ai/glm-5.1

Compare with GLM 5, GLM 5 Turbo, GLM 5V Turbo

CompareGLM 5.1
  • Crusoe100%
    Healthy24h 99.72%
    7d
    99.40%
    30d
    99.40%
    p50
    635ms
    p99
    2.73s
    Throughput
    48 tps
    Context
    203K
    $/Mtok
    $1.20 / $4.40
    crusoe/fp8fp8
  • Degraded24h 96.38%
    7d
    93.86%
    30d
    93.86%
    p50
    1.17s
    p99
    21.4s
    Throughput
    19 tps
    Context
    164K
    $/Mtok
    $1.30 / $4.30
    digitalocean
  • Healthy24h 99.96%
    7d
    99.96%
    30d
    99.96%
    p50
    262ms
    p99
    7.09s
    Throughput
    85 tps
    Context
    203K
    $/Mtok
    $1.40 / $4.40
    friendli
  • Healthy24h 99.63%
    7d
    99.62%
    30d
    99.62%
    p50
    2.29s
    p99
    8.44s
    Throughput
    45 tps
    Context
    203K
    $/Mtok
    $0.910 / $2.86
    gmicloud/fp8fp8
  • Nebius100%
    Healthy24h 97.78%
    7d
    97.38%
    30d
    97.38%
    p50
    883ms
    p99
    10.9s
    Throughput
    25 tps
    Context
    203K
    $/Mtok
    $1.40 / $4.40
    nebius/fp8fp8
  • Healthy24h 99.92%
    7d
    99.88%
    30d
    99.88%
    p50
    1.80s
    p99
    7.27s
    Throughput
    45 tps
    Context
    205K
    $/Mtok
    $1.19 / $3.74
    siliconflow/fp8fp8
  • Healthy24h 99.29%
    7d
    98.74%
    30d
    98.74%
    p50
    2.54s
    p99
    10.7s
    Throughput
    23 tps
    Context
    200K
    $/Mtok
    $0.966 / $3.04
    streamlake/fp8fp8
  • Z.AI100%
    Healthy24h 99.58%
    7d
    99.01%
    30d
    99.01%
    p50
    4.55s
    p99
    7.24s
    Throughput
    19 tps
    Context
    203K
    $/Mtok
    $1.40 / $4.40
    z-ai/fp8fp8
  • DeepInfra99.55%
    Healthy24h 99.43%
    7d
    99.35%
    30d
    99.35%
    p50
    1.09s
    p99
    20.4s
    Throughput
    21 tps
    Context
    203K
    $/Mtok
    $1.05 / $3.50
    deepinfra/fp4fp4
  • Healthy24h 99.80%
    7d
    99.76%
    30d
    99.76%
    p50
    1.51s
    p99
    10.3s
    Throughput
    49 tps
    Context
    203K
    $/Mtok
    $1.26 / $3.96
    atlas-cloud/fp8fp8
  • No data24h 99.85%
    7d
    99.75%
    30d
    99.75%
    p50
    1.83s
    p99
    3.04s
    Throughput
    57 tps
    Context
    203K
    $/Mtok
    $1.33 / $4.18
    alibaba/fp8fp8
  • No data24h 99.96%
    7d
    99.89%
    30d
    99.89%
    p50
    907ms
    p99
    16.0s
    Throughput
    74 tps
    Context
    203K
    $/Mtok
    $1.40 / $4.40
    baidu/fp8fp8
  • No data24h 80.52%
    7d
    83.50%
    30d
    83.50%
    p50
    2.65s
    p99
    86.0s
    Throughput
    26 tps
    Context
    203K
    $/Mtok
    $0.980 / $3.08
    chutes/fp8fp8
  • No data24h 99.86%
    7d
    99.33%
    30d
    99.33%
    p50
    2.24s
    p99
    7.42s
    Throughput
    48 tps
    Context
    205K
    $/Mtok
    $1.38 / $4.40
    novita/fp8fp8
  • No data24h 99.19%
    7d
    99.57%
    30d
    99.57%
    p50
    477ms
    p99
    13.7s
    Throughput
    109 tps
    Context
    203K
    $/Mtok
    $1.40 / $4.40
    parasail/fp8fp8
  • No data24h 80.09%
    7d
    83.55%
    30d
    83.55%
    p50
    2.25s
    p99
    21.9s
    Throughput
    28 tps
    Context
    203K
    $/Mtok
    $1.21 / $4.20
    phala
  • No data24h 97.46%
    7d
    96.17%
    30d
    96.17%
    p50
    1.40s
    p99
    12.7s
    Throughput
    30 tps
    Context
    200K
    $/Mtok
    $1.54 / $4.84
    venice/fp8fp8

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

Price changes

  • GLM 5.1DigitalOceandigitalocean$0.975 / $4.30$1.30 / $4.302026-08-21 03:31 UTC
  • GLM 5.1Baidubaidu/fp8$0.896 / $2.82$1.40 / $4.402026-08-20 23:41 UTC
  • GLM 5.1Baidubaidu/fp8$1.04 / $3.26$0.896 / $2.822026-08-20 13:46 UTC
  • GLM 5.1Baidubaidu/fp8$1.40 / $4.40$1.04 / $3.262026-08-20 12:46 UTC
  • GLM 5.1Baidubaidu/fp8$0.896 / $2.82$1.40 / $4.402026-08-19 23:40 UTC
  • GLM 5.1Baidubaidu/fp8$0.952 / $2.99$0.896 / $2.822026-08-19 13:45 UTC
  • GLM 5.1Baidubaidu/fp8$1.40 / $4.40$0.952 / $2.992026-08-19 12:40 UTC

7 endpoints reporting no data are omitted from the charts.

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.