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 99.76%
    7d
    99.35%
    30d
    99.35%
    p50
    1.57s
    p99
    6.07s (best)
    Throughput
    110 tps (best)
    Context
    262K
    $/Mtok
    $0.200 / $0.800
    atlas-cloud/fp8fp8
  • Baidu100% (best)
    Healthy24h 99.60%
    7d
    99.22%
    30d
    99.22%
    p50
    1.22s
    p99
    10.1s
    Throughput
    48 tps
    Context
    262K
    $/Mtok
    $0.125 / $0.502 (best)
    baidu/fp8fp8
  • DeepInfra100% (best)
    Healthy24h 96.00%
    7d
    97.60%
    30d
    97.60%
    p50
    571ms (best)
    p99
    7.34s
    Throughput
    48 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.580
    deepinfra/fp8fp8
  • GMICloud100% (best)
    Healthy24h 97.92%
    7d
    97.11%
    30d
    97.11%
    p50
    2.35s
    p99
    17.0s
    Throughput
    103 tps
    Context
    262K
    $/Mtok
    $0.126 / $0.522
    gmicloud/bf16bf16
  • Novita100% (best)
    Healthy24h 98.91%
    7d
    98.98%
    30d
    98.98%
    p50
    2.60s
    p99
    14.2s
    Throughput
    68 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.580
    novita
  • Tencent100% (best)
    Healthy24h 99.80%
    7d
    99.68% (best)
    30d
    99.68% (best)
    p50
    2.57s
    p99
    13.7s
    Throughput
    64 tps
    Context
    262K
    $/Mtok
    $0.132 / $0.528
    tencent/fp8fp8
  • No data24h
    7d
    30d
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.150 / $0.640
    phala

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, averaged over the hour.

Throughput

Median tokens per second.