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
  • Mancer 2100%
    Healthy24h 96.65%
    p50
    1.41s
    p99
    13.4s
    Throughput
    14 tps
    Context
    131K
    $/Mtok
    $0.600 / $2.50
    mancer/fp4fp4
  • Venice100%
    Healthy24h 98.05%
    p50
    1.79s
    p99
    19.0s
    Throughput
    17 tps
    Context
    198K
    $/Mtok
    $0.550 / $2.65
    venice/fp4fp4
  • DeepInfra99.67%
    Healthy24h 98.94%
    p50
    1.39s
    p99
    20.0s
    Throughput
    17 tps
    Context
    203K
    $/Mtok
    $0.400 / $1.75
    deepinfra/fp4fp4
  • Google99.50%
    Healthy24h 99.88%
    p50
    471ms
    p99
    11.3s
    Throughput
    102 tps
    Context
    200K
    $/Mtok
    $0.600 / $2.20
    google-vertex
  • AtlasCloud98.13%
    Healthy24h 96.90%
    p50
    1.93s
    p99
    22.9s
    Throughput
    35 tps
    Context
    203K
    $/Mtok
    $0.520 / $1.85
    atlas-cloud/fp8fp8
  • StreamLake97.62%
    Degraded24h 92.39%
    p50
    1.65s
    p99
    17.8s
    Throughput
    28 tps
    Context
    200K
    $/Mtok
    $0.480 / $1.76
    streamlake/fp8fp8
  • Novita96.36%
    Degraded24h 93.46%
    p50
    2.08s
    p99
    31.1s
    Throughput
    26 tps
    Context
    205K
    $/Mtok
    $0.540 / $1.98
    novita/fp8fp8
  • Z.AI95.18%
    Degraded24h 84.73%
    p50
    13.9s
    p99
    34.0s
    Throughput
    31 tps
    Context
    203K
    $/Mtok
    $0.600 / $2.20
    z-ai/fp4fp4

Measured 2m 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.