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
  • AtlasCloud100%
    Healthy24h 96.88%
    p50
    843ms
    p99
    2.58s
    Throughput
    10 tps
    Context
    262K
    $/Mtok
    $0.550 / $3.50
    atlas-cloud/fp8fp8
  • DeepInfra100%
    Healthy24h 97.65%
    p50
    487ms
    p99
    169s
    Throughput
    32 tps
    Context
    262K
    $/Mtok
    $0.450 / $3.00
    deepinfra/fp8fp8
  • DigitalOcean100%
    Healthy24h 96.29%
    p50
    771ms
    p99
    4.60s
    Throughput
    10 tps
    Context
    131K
    $/Mtok
    $0.302 / $1.93
    digitalocean
  • Parasail100%
    Healthy24h 99.49%
    p50
    783ms
    p99
    2.19s
    Throughput
    59 tps
    Context
    262K
    $/Mtok
    $0.500 / $3.60
    parasail/fp8fp8
  • Phala100%
    Healthy24h 97.82%
    p50
    1.66s
    p99
    7.60s
    Throughput
    45 tps
    Context
    262K
    $/Mtok
    $0.550 / $3.50
    phala
  • StreamLake100%
    Healthy24h 98.37%
    p50
    1.60s
    p99
    3.28s
    Throughput
    179 tps
    Context
    256K
    $/Mtok
    $0.600 / $3.60
    streamlake
  • Alibaba
    No data24h 98.49%
    p50
    1.14s
    p99
    5.57s
    Throughput
    52 tps
    Context
    262K
    $/Mtok
    $0.390 / $2.34
    alibaba
  • GMICloud
    No data24h 0.00%
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.600 / $3.60
    gmicloud/fp8fp8
  • Novita
    No data24h 96.34%
    p50
    746ms
    p99
    3.79s
    Throughput
    47 tps
    Context
    262K
    $/Mtok
    $0.600 / $3.60
    novita
  • Venice
    No data24h 97.99%
    p50
    1.85s
    p99
    8.08s
    Throughput
    64 tps
    Context
    128K
    $/Mtok
    $0.750 / $4.50
    venice

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

4 endpoints reporting no data are omitted from the charts.

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 and p99 are OpenRouter's rolling 30-minute windows.

Throughput

Median tokens per second.