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
  • DeepInfra100%
    Healthy24h 99.01%
    p50
    1.24s
    p99
    8.38s
    Throughput
    18 tps
    Context
    203K
    $/Mtok
    $0.400 / $1.75
    deepinfra/fp4fp4
  • Google100%
    Healthy24h 99.87%
    p50
    470ms
    p99
    12.3s
    Throughput
    108 tps
    Context
    200K
    $/Mtok
    $0.600 / $2.20
    google-vertex
  • Mancer 2100%
    Healthy24h 96.90%
    p50
    1.32s
    p99
    7.47s
    Throughput
    16 tps
    Context
    131K
    $/Mtok
    $0.600 / $2.50
    mancer/fp4fp4
  • StreamLake100%
    Healthy24h 92.39%
    p50
    1.84s
    p99
    24.2s
    Throughput
    34 tps
    Context
    200K
    $/Mtok
    $0.480 / $1.76
    streamlake/fp8fp8
  • Venice100%
    Healthy24h 98.40%
    p50
    1.52s
    p99
    7.61s
    Throughput
    18 tps
    Context
    198K
    $/Mtok
    $0.550 / $2.65
    venice/fp4fp4
  • AtlasCloud99.58%
    Healthy24h 96.88%
    p50
    1.99s
    p99
    16.1s
    Throughput
    35 tps
    Context
    203K
    $/Mtok
    $0.520 / $1.85
    atlas-cloud/fp8fp8
  • Novita97.50%
    Healthy24h 93.43%
    p50
    2.36s
    p99
    42.5s
    Throughput
    24 tps
    Context
    205K
    $/Mtok
    $0.540 / $1.98
    novita/fp8fp8
  • Z.AI92.38%
    Degraded24h 86.75%
    p50
    14.3s
    p99
    25.2s
    Throughput
    29 tps
    Context
    203K
    $/Mtok
    $0.600 / $2.20
    z-ai/fp4fp4

Measured 3m 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.

Throughput

Median tokens per second.