modelstatus.dev

GLM 5

z-ai/glm-5

Compare with GLM 5 Turbo, GLM 5V Turbo, GLM 5.1

CompareGLM 5
  • AtlasCloud100%
    Healthy24h 99.56%
    p50
    1.96s
    p99
    5.35s
    Throughput
    39 tps
    Context
    203K
    $/Mtok
    $0.950 / $3.15
    atlas-cloud/fp8fp8
  • Baidu100%
    Healthy24h 99.90%
    p50
    1.06s
    p99
    2.30s
    Throughput
    51 tps
    Context
    203K
    $/Mtok
    $0.700 / $2.24
    baidu/fp8fp8
  • DeepInfra100%
    Healthy24h 98.88%
    p50
    842ms
    p99
    10.1s
    Throughput
    29 tps
    Context
    203K
    $/Mtok
    $0.600 / $2.08
    deepinfra/fp4fp4
  • Novita100%
    Healthy24h 99.94%
    p50
    1.52s
    p99
    8.18s
    Throughput
    57 tps
    Context
    203K
    $/Mtok
    $1.00 / $3.20
    novita/fp8fp8
  • Z.AI100%
    Healthy24h 99.35%
    p50
    8.32s
    p99
    11.6s
    Throughput
    52 tps
    Context
    203K
    $/Mtok
    $1.00 / $3.20
    z-ai/fp8fp8
  • StreamLake99.79%
    Healthy24h 99.92%
    p50
    2.20s
    p99
    5.59s
    Throughput
    60 tps
    Context
    198K
    $/Mtok
    $0.600 / $1.92
    streamlake/fp8fp8
  • GMICloud98.48%
    Healthy24h 99.52%
    p50
    1.59s
    p99
    8.68s
    Throughput
    48 tps
    Context
    203K
    $/Mtok
    $0.600 / $1.92
    gmicloud/fp8fp8
  • Amazon Bedrock98.25%
    Healthy24h 92.59%
    p50
    1.19s
    p99
    3.73s
    Throughput
    104 tps
    Context
    203K
    $/Mtok
    $1.00 / $3.20
    amazon-bedrock
  • DigitalOcean89.19%
    Down24h 93.60%
    p50
    1.52s
    p99
    16.6s
    Throughput
    7.0 tps
    Context
    64K
    $/Mtok
    $0.750 / $2.40
    digitalocean
  • SiliconFlow
    No data24h 99.75%
    p50
    2.32s
    p99
    11.7s
    Throughput
    46 tps
    Context
    205K
    $/Mtok
    $0.950 / $2.55
    siliconflow/fp8fp8
  • Venice
    No data24h 93.61%
    p50
    1.22s
    p99
    7.38s
    Throughput
    29 tps
    Context
    198K
    $/Mtok
    $1.00 / $3.20
    venice/fp8fp8

Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

2 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 and p99 are OpenRouter's rolling 30-minute windows.

Throughput

Median tokens per second.