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.

  • DeepInfra99.89% (best)
    Healthy24h 99.73%
    7d
    99.33% (best)
    30d
    99.33% (best)
    p50
    419ms
    p99
    3.97s
    Throughput
    17 tps
    Context
    203K
    $/Mtok
    $0.060 / $0.400 (best)
    deepinfra/bf16bf16
  • Venice98.33%
    Healthy24h 99.28%
    7d
    98.49%
    30d
    98.49%
    p50
    673ms
    p99
    3.50s (best)
    Throughput
    18 tps
    Context
    128K
    $/Mtok
    $0.060 / $0.400 (best)
    venice/fp8fp8
  • Degraded24h 96.62%
    7d
    96.46%
    30d
    96.46%
    p50
    390ms (best)
    p99
    19.2s
    Throughput
    22 tps
    Context
    131K
    $/Mtok
    $0.061 / $0.400
    cloudflare
  • Novita87.97%
    Down24h 79.90%
    7d
    80.67%
    30d
    80.67%
    p50
    897ms
    p99
    40.6s
    Throughput
    36 tps (best)
    Context
    200K
    $/Mtok
    $0.070 / $0.400
    novita/bf16bf16

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, averaged over the hour.

Throughput

Median tokens per second.