modelstatus.dev

GLM 4.7 Flash

z-ai/glm-4.7-flash

Compare with GLM 4.7, GLM 4.6, GLM 4.6V

CompareGLM 4.7 Flash
  • DeepInfra99.24%
    Healthy24h 99.55%
    p50
    364ms
    p99
    4.26s
    Throughput
    16 tps
    Context
    203K
    $/Mtok
    $0.060 / $0.400
    deepinfra/bf16bf16
  • Cloudflare97.19%
    Healthy24h 98.16%
    p50
    409ms
    p99
    8.04s
    Throughput
    24 tps
    Context
    131K
    $/Mtok
    $0.061 / $0.400
    cloudflare
  • Venice96.49%
    Healthy24h 98.00%
    p50
    586ms
    p99
    5.94s
    Throughput
    37 tps
    Context
    128K
    $/Mtok
    $0.060 / $0.400
    venice/fp8fp8
  • Novita78.57%
    Down24h 93.66%
    p50
    1.65s
    p99
    132s
    Throughput
    33 tps
    Context
    200K
    $/Mtok
    $0.070 / $0.400
    novita/bf16bf16

Measured 1m 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.