modelstatus.dev

Hy3

Hy3: providers compared

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

  • AtlasCloud100% (best)
    Healthy24h 99.77%
    7d
    99.34%
    30d
    99.34%
    p50
    1.74s
    p99
    6.63s (best)
    Throughput
    115 tps (best)
    Context
    262K
    $/Mtok
    $0.200 / $0.800
    atlas-cloud/fp8fp8
  • GMICloud100% (best)
    Healthy24h 97.93%
    7d
    97.10%
    30d
    97.10%
    p50
    2.25s
    p99
    25.7s
    Throughput
    55 tps
    Context
    262K
    $/Mtok
    $0.126 / $0.522
    gmicloud/bf16bf16
  • Novita100% (best)
    Healthy24h 98.90%
    7d
    98.97%
    30d
    98.97%
    p50
    2.39s
    p99
    14.4s
    Throughput
    61 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.580
    novita
  • Baidu99.82%
    Healthy24h 99.57%
    7d
    99.21%
    30d
    99.21%
    p50
    950ms
    p99
    8.99s
    Throughput
    60 tps
    Context
    262K
    $/Mtok
    $0.125 / $0.502 (best)
    baidu/fp8fp8
  • Tencent99.64%
    Healthy24h 99.81%
    7d
    99.67% (best)
    30d
    99.67% (best)
    p50
    2.65s
    p99
    16.7s
    Throughput
    63 tps
    Context
    262K
    $/Mtok
    $0.132 / $0.528
    tencent/fp8fp8
  • No data24h 95.92%
    7d
    97.56%
    30d
    97.56%
    p50
    559ms (best)
    p99
    22.1s
    Throughput
    44 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.580
    deepinfra/fp8fp8

Measured 2m 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.