modelstatus.dev

GLM 4.7

z-ai/glm-4.7

Compare with GLM 4.7 Flash, GLM 4.6, GLM 4.6V

CompareGLM 4.7
  • Google100%
    Healthy24h 99.83%
    p50
    534ms
    p99
    12.4s
    Throughput
    113 tps
    Context
    200K
    $/Mtok
    $0.600 / $2.20
    google-vertex
  • Mancer 2100%
    Healthy24h 97.06%
    p50
    1.31s
    p99
    16.7s
    Throughput
    14 tps
    Context
    131K
    $/Mtok
    $0.600 / $2.50
    mancer/fp4fp4
  • Venice100%
    Healthy24h 98.39%
    p50
    1.50s
    p99
    18.6s
    Throughput
    15 tps
    Context
    198K
    $/Mtok
    $0.550 / $2.65
    venice/fp4fp4
  • AtlasCloud99.76%
    Healthy24h 96.84%
    p50
    2.03s
    p99
    18.4s
    Throughput
    42 tps
    Context
    203K
    $/Mtok
    $0.520 / $1.85
    atlas-cloud/fp8fp8
  • StreamLake98.84%
    Healthy24h 92.34%
    p50
    2.63s
    p99
    32.3s
    Throughput
    40 tps
    Context
    200K
    $/Mtok
    $0.480 / $1.76
    streamlake/fp8fp8
  • DeepInfra97.04%
    Healthy24h 99.05%
    p50
    1.29s
    p99
    22.1s
    Throughput
    16 tps
    Context
    203K
    $/Mtok
    $0.400 / $1.75
    deepinfra/fp4fp4
  • Novita94.52%
    Degraded24h 93.33%
    p50
    2.58s
    p99
    31.1s
    Throughput
    27 tps
    Context
    205K
    $/Mtok
    $0.540 / $1.98
    novita/fp8fp8
  • Z.AI90.69%
    Degraded24h 88.93%
    p50
    13.0s
    p99
    32.8s
    Throughput
    35 tps
    Context
    203K
    $/Mtok
    $0.600 / $2.20
    z-ai/fp4fp4

Measured 53s ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

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.