modelstatus.dev

Qwen3.5 397B A17B

Qwen3.5 397B A17B: providers compared

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

  • Alibaba100% (best)
    Healthy24h 98.76%
    7d
    98.03%
    30d
    98.03%
    p50
    976ms
    p99
    3.91s
    Throughput
    52 tps (best)
    Context
    262K
    $/Mtok
    $0.390 / $2.34 (best)
    alibaba
  • AtlasCloud100% (best)
    Healthy24h 96.45%
    7d
    96.26%
    30d
    96.26%
    p50
    920ms
    p99
    3.21s (best)
    Throughput
    7.0 tps
    Context
    262K
    $/Mtok
    $0.550 / $3.50
    atlas-cloud/fp8fp8
  • DigitalOcean100% (best)
    Healthy24h 97.23%
    7d
    94.58%
    30d
    94.58%
    p50
    1.28s
    p99
    9.00s
    Throughput
    8.0 tps
    Context
    131K
    $/Mtok
    $0.550 / $3.50
    digitalocean
  • Phala100% (best)
    Healthy24h 96.81%
    7d
    96.49%
    30d
    96.49%
    p50
    1.93s
    p99
    7.10s
    Throughput
    10 tps
    Context
    262K
    $/Mtok
    $0.550 / $3.50
    phala
  • StreamLake100% (best)
    Healthy24h 97.98%
    7d
    97.34%
    30d
    97.34%
    p50
    1.78s
    p99
    4.18s
    Throughput
    23 tps
    Context
    256K
    $/Mtok
    $0.600 / $3.60
    streamlake
  • Parasail99.82%
    Healthy24h 98.18%
    7d
    97.17%
    30d
    97.17%
    p50
    694ms
    p99
    21.4s
    Throughput
    43 tps
    Context
    262K
    $/Mtok
    $0.500 / $3.60
    parasail/fp8fp8
  • DeepInfra99.24%
    Healthy24h 99.03%
    7d
    98.31% (best)
    30d
    98.31% (best)
    p50
    402ms (best)
    p99
    7.70s
    Throughput
    26 tps
    Context
    262K
    $/Mtok
    $0.450 / $3.00
    deepinfra/fp8fp8
  • No data24h 0.00%
    7d
    0.00%
    30d
    0.00%
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.600 / $3.60
    gmicloud/fp8fp8
  • No data24h 95.84%
    7d
    96.02%
    30d
    96.02%
    p50
    1.82s
    p99
    3.81s
    Throughput
    45 tps
    Context
    262K
    $/Mtok
    $0.600 / $3.60
    novita
  • Degraded24h 94.00%
    7d
    95.86%
    30d
    95.86%
    p50
    1.55s
    p99
    22.0s
    Throughput
    18 tps
    Context
    128K
    $/Mtok
    $0.750 / $4.50
    venice

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.