modelstatus.dev

GLM 4.6

z-ai/glm-4.6

Compare with GLM 4.6V, GLM 4.5 Air, GLM 4.5V

CompareGLM 4.6
  • Healthy24h 99.92%
    7d
    99.16%
    30d
    99.16%
    p50
    524ms
    p99
    10.3s
    Throughput
    42 tps
    Context
    203K
    $/Mtok
    $0.500 / $2.00
    deepinfra/fp4fp4
  • Venice100%
    Healthy24h 99.34%
    7d
    98.74%
    30d
    98.74%
    p50
    1.12s
    p99
    19.6s
    Throughput
    27 tps
    Context
    198K
    $/Mtok
    $0.430 / $1.75
    venice/fp4fp4
  • Novita96.00%
    Healthy24h 97.26%
    7d
    96.76%
    30d
    96.76%
    p50
    2.02s
    p99
    27.7s
    Throughput
    27 tps
    Context
    205K
    $/Mtok
    $0.550 / $2.20
    novita/bf16bf16
  • No data24h 92.69%
    7d
    97.11%
    30d
    97.11%
    p50
    905ms
    p99
    11.9s
    Throughput
    47 tps
    Context
    203K
    $/Mtok
    $0.600 / $2.20
    atlas-cloud/fp8fp8
  • Z.AI
    No data24h 95.76%
    7d
    91.74%
    30d
    91.74%
    p50
    1.01s
    p99
    23.5s
    Throughput
    28 tps
    Context
    203K
    $/Mtok
    $0.600 / $2.20
    z-ai/fp4fp4

Measured 5m 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 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.