modelstatus.dev

Qwen3.5 397B A17B

qwen/qwen3.5-397b-a17b

Compare with Qwen3.5-35B-A3B, Qwen3.5-27B, Qwen3.5-122B-A10B

CompareQwen3.5 397B A17B
  • Healthy24h 98.93%
    7d
    97.71%
    30d
    97.71%
    p50
    902ms
    p99
    8.84s
    Throughput
    26 tps
    Context
    262K
    $/Mtok
    $0.390 / $2.34
    alibaba
  • Novita100%
    Healthy24h 97.35%
    7d
    95.42%
    30d
    95.42%
    p50
    1.19s
    p99
    7.43s
    Throughput
    22 tps
    Context
    262K
    $/Mtok
    $0.600 / $3.60
    novita
  • Healthy24h 96.58%
    7d
    95.95%
    30d
    95.95%
    p50
    1.09s
    p99
    7.25s
    Throughput
    12 tps
    Context
    262K
    $/Mtok
    $0.550 / $3.50
    atlas-cloud/fp8fp8
  • Healthy24h 96.83%
    7d
    97.08%
    30d
    97.08%
    p50
    2.52s
    p99
    4.50s
    Throughput
    30 tps
    Context
    256K
    $/Mtok
    $0.600 / $3.60
    streamlake
  • Parasail96.05%
    Healthy24h 97.42%
    7d
    97.32%
    30d
    97.32%
    p50
    639ms
    p99
    44.6s
    Throughput
    56 tps
    Context
    262K
    $/Mtok
    $0.500 / $3.60
    parasail/fp8fp8
  • DeepInfra93.88%
    Degraded24h 98.75%
    7d
    98.11%
    30d
    98.11%
    p50
    505ms
    p99
    8.75s
    Throughput
    29 tps
    Context
    262K
    $/Mtok
    $0.450 / $3.00
    deepinfra/fp8fp8
  • Venice84.38%
    Down24h 94.76%
    7d
    95.49%
    30d
    95.49%
    p50
    1.91s
    p99
    10.6s
    Throughput
    34 tps
    Context
    128K
    $/Mtok
    $0.750 / $4.50
    venice
  • Phala84.20%
    Down24h 95.07%
    7d
    96.19%
    30d
    96.19%
    p50
    2.03s
    p99
    84.6s
    Throughput
    26 tps
    Context
    262K
    $/Mtok
    $0.550 / $3.50
    phala
  • Down24h 97.72%
    7d
    95.21%
    30d
    95.21%
    p50
    1.54s
    p99
    11.4s
    Throughput
    9.0 tps
    Context
    131K
    $/Mtok
    $0.550 / $3.50
    digitalocean
  • Down24h 0.00%
    7d
    0.00%
    30d
    0.00%
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.600 / $3.60
    gmicloud/fp8fp8

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

Price changes

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.