modelstatus.dev

GLM 5.1

z-ai/glm-5.1

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

CompareGLM 5.1
  • Healthy24h 99.82%
    7d
    99.76%
    30d
    99.76%
    p50
    1.61s
    p99
    8.34s
    Throughput
    48 tps
    Context
    203K
    $/Mtok
    $1.26 / $3.96
    atlas-cloud/fp8fp8
  • Baidu100%
    Healthy24h 99.96%
    7d
    99.89%
    30d
    99.89%
    p50
    963ms
    p99
    4.48s
    Throughput
    64 tps
    Context
    203K
    $/Mtok
    $1.40 / $4.40
    baidu/fp8fp8
  • Crusoe100%
    Healthy24h 99.71%
    7d
    99.41%
    30d
    99.41%
    p50
    613ms
    p99
    4.84s
    Throughput
    62 tps
    Context
    203K
    $/Mtok
    $1.20 / $4.40
    crusoe/fp8fp8
  • Healthy24h 99.47%
    7d
    99.36%
    30d
    99.36%
    p50
    1.00s
    p99
    11.1s
    Throughput
    31 tps
    Context
    203K
    $/Mtok
    $1.05 / $3.50
    deepinfra/fp4fp4
  • Healthy24h 99.96%
    7d
    99.95%
    30d
    99.95%
    p50
    246ms
    p99
    6.24s
    Throughput
    61 tps
    Context
    203K
    $/Mtok
    $1.40 / $4.40
    friendli
  • Healthy24h 99.68%
    7d
    99.63%
    30d
    99.63%
    p50
    2.02s
    p99
    10.4s
    Throughput
    45 tps
    Context
    203K
    $/Mtok
    $0.910 / $2.86
    gmicloud/fp8fp8
  • Healthy24h 99.93%
    7d
    99.88%
    30d
    99.88%
    p50
    1.84s
    p99
    5.99s
    Throughput
    45 tps
    Context
    205K
    $/Mtok
    $1.19 / $3.74
    siliconflow/fp8fp8
  • Healthy24h 99.35%
    7d
    98.75%
    30d
    98.75%
    p50
    2.69s
    p99
    12.2s
    Throughput
    22 tps
    Context
    200K
    $/Mtok
    $0.966 / $3.04
    streamlake/fp8fp8
  • Z.AI100%
    Healthy24h 99.62%
    7d
    99.03%
    30d
    99.03%
    p50
    4.71s
    p99
    7.13s
    Throughput
    22 tps
    Context
    203K
    $/Mtok
    $1.40 / $4.40
    z-ai/fp8fp8
  • No data24h 99.86%
    7d
    99.76%
    30d
    99.76%
    p50
    2.08s
    p99
    3.50s
    Throughput
    47 tps
    Context
    203K
    $/Mtok
    $1.33 / $4.18
    alibaba/fp8fp8
  • No data24h 79.90%
    7d
    83.13%
    30d
    83.13%
    p50
    3.24s
    p99
    84.0s
    Throughput
    28 tps
    Context
    203K
    $/Mtok
    $0.980 / $3.08
    chutes/fp8fp8
  • No data24h 96.36%
    7d
    93.67%
    30d
    93.67%
    p50
    1.12s
    p99
    8.73s
    Throughput
    23 tps
    Context
    164K
    $/Mtok
    $1.30 / $4.30
    digitalocean
  • No data24h 97.81%
    7d
    97.41%
    30d
    97.41%
    p50
    1.25s
    p99
    16.0s
    Throughput
    31 tps
    Context
    203K
    $/Mtok
    $1.40 / $4.40
    nebius/fp8fp8
  • No data24h 99.87%
    7d
    99.33%
    30d
    99.33%
    p50
    3.31s
    p99
    52.7s
    Throughput
    27 tps
    Context
    205K
    $/Mtok
    $1.38 / $4.40
    novita/fp8fp8
  • No data24h 99.16%
    7d
    99.56%
    30d
    99.56%
    p50
    397ms
    p99
    9.26s
    Throughput
    100 tps
    Context
    203K
    $/Mtok
    $1.40 / $4.40
    parasail/fp8fp8
  • Degraded24h 79.71%
    7d
    83.55%
    30d
    83.55%
    p50
    3.12s
    p99
    39.8s
    Throughput
    23 tps
    Context
    203K
    $/Mtok
    $1.21 / $4.20
    phala
  • No data24h 97.92%
    7d
    96.26%
    30d
    96.26%
    p50
    1.34s
    p99
    8.55s
    Throughput
    51 tps
    Context
    200K
    $/Mtok
    $1.54 / $4.84
    venice/fp8fp8

Measured 4m 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.