modelstatus.dev

GLM 4.7 Flash

GLM 4.7 Flash: providers compared

Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.

  • DeepInfra100% (best)
    Healthy24h 99.73%
    7d
    99.32% (best)
    30d
    99.32% (best)
    p50
    422ms (best)
    p99
    5.13s (best)
    Throughput
    16 tps (best)
    Context
    203K
    $/Mtok
    $0.060 / $0.400 (best)
    deepinfra/bf16bf16
  • Venice100% (best)
    Healthy24h 99.28%
    7d
    98.47%
    30d
    98.47%
    p50
    774ms
    p99
    8.71s
    Throughput
    11 tps
    Context
    128K
    $/Mtok
    $0.060 / $0.400 (best)
    venice/fp8fp8
  • Novita74.10%
    Down24h 81.22%
    7d
    80.69%
    30d
    80.69%
    p50
    1.33s
    p99
    138s
    Throughput
    16 tps (best)
    Context
    200K
    $/Mtok
    $0.070 / $0.400
    novita/bf16bf16
  • Down24h 96.76%
    7d
    96.71%
    30d
    96.71%
    p50
    568ms
    p99
    79.9s
    Throughput
    16 tps (best)
    Context
    131K
    $/Mtok
    $0.061 / $0.400
    cloudflare

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

History

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.