modelstatus.dev

GLM 5

z-ai/glm-5

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

CompareGLM 5
  • Amazon Bedrock100%
    Healthy24h 92.69%
    p50
    1.30s
    p99
    4.89s
    Throughput
    98 tps
    Context
    203K
    $/Mtok
    $1.00 / $3.20
    amazon-bedrock
  • AtlasCloud100%
    Healthy24h 99.55%
    p50
    2.41s
    p99
    10.3s
    Throughput
    38 tps
    Context
    203K
    $/Mtok
    $0.950 / $3.15
    atlas-cloud/fp8fp8
  • Novita100%
    Healthy24h 99.94%
    p50
    1.64s
    p99
    10.3s
    Throughput
    56 tps
    Context
    203K
    $/Mtok
    $1.00 / $3.20
    novita/fp8fp8
  • SiliconFlow100%
    Healthy24h 99.76%
    p50
    2.58s
    p99
    13.2s
    Throughput
    40 tps
    Context
    205K
    $/Mtok
    $0.950 / $2.55
    siliconflow/fp8fp8
  • StreamLake100%
    Healthy24h 99.92%
    p50
    2.51s
    p99
    7.49s
    Throughput
    37 tps
    Context
    198K
    $/Mtok
    $0.600 / $1.92
    streamlake/fp8fp8
  • Z.AI100%
    Healthy24h 99.37%
    p50
    8.22s
    p99
    12.3s
    Throughput
    53 tps
    Context
    203K
    $/Mtok
    $1.00 / $3.20
    z-ai/fp8fp8
  • DigitalOcean98.00%
    Healthy24h 93.53%
    p50
    1.19s
    p99
    16.0s
    Throughput
    7.0 tps
    Context
    64K
    $/Mtok
    $0.750 / $2.40
    digitalocean
  • Baidu97.67%
    Healthy24h 99.90%
    p50
    1.06s
    p99
    11.9s
    Throughput
    36 tps
    Context
    203K
    $/Mtok
    $0.700 / $2.24
    baidu/fp8fp8
  • GMICloud97.67%
    Healthy24h 99.51%
    p50
    1.28s
    p99
    6.88s
    Throughput
    64 tps
    Context
    203K
    $/Mtok
    $0.600 / $1.92
    gmicloud/fp8fp8
  • DeepInfra
    No data24h 98.85%
    p50
    816ms
    p99
    6.66s
    Throughput
    40 tps
    Context
    203K
    $/Mtok
    $0.600 / $2.08
    deepinfra/fp4fp4
  • Venice
    No data24h 93.53%
    p50
    1.03s
    p99
    15.4s
    Throughput
    42 tps
    Context
    198K
    $/Mtok
    $1.00 / $3.20
    venice/fp8fp8

Measured 3m 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, averaged over the hour.

Throughput

Median tokens per second.