modelstatus.dev

Qwen3.5-35B-A3B

qwen/qwen3.5-35b-a3bInputtextimagevideoOutputtext

Compare its 9 providersIncident RSSCompare with Qwen3.5 397B A17B, Qwen3.5-27B, Qwen3.5-9B

CompareQwen3.5-35B-A3B
  • Healthy24h 98.53%
    7d
    98.97%
    30d
    98.58%
    p50
    1.40s
    p99
    2.69s
    Throughput
    63 tps
    Context
    262K
    $/Mtok
    $0.225 / $1.80
    atlas-cloud/fp8fp8
  • Healthy24h 99.86%
    7d
    99.74%
    30d
    99.66%
    p50
    606ms
    p99
    15.2s
    Throughput
    53 tps
    Context
    262K
    $/Mtok
    $0.080 / $0.750
    darkbloom/fp4fp4
  • Healthy24h 99.42%
    7d
    99.80%
    30d
    98.77%
    p50
    698ms
    p99
    2.39s
    Throughput
    57 tps
    Context
    262K
    $/Mtok
    $0.140 / $1.00
    deepinfra/fp8fp8
  • Healthy24h 98.97%
    7d
    99.87%
    30d
    99.81%
    p50
    721ms
    p99
    6.98s
    Throughput
    119 tps
    Context
    262K
    $/Mtok
    $0.150 / $1.00
    parasail/fp8fp8
  • Healthy24h 94.92%
    7d
    95.51%
    30d
    94.35%
    p50
    1.45s
    p99
    6.38s
    Throughput
    36 tps
    Context
    262K
    $/Mtok
    $0.240 / $1.80
    siliconflow/fp8fp8
  • Venice100%
    Healthy24h 99.88%
    7d
    99.91%
    30d
    99.92%
    p50
    676ms
    p99
    2.08s
    Throughput
    156 tps
    Context
    256K
    $/Mtok
    $0.313 / $1.25
    venice
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    262K
    $/Mtok
    $0.140 / $1.00
    akashml/fp8fp8
  • Down24h 76.55%
    7d
    90.68%
    30d
    96.41%
    p50
    602ms
    p99
    1.22s
    Throughput
    96 tps
    Context
    262K
    $/Mtok
    $0.163 / $1.30
    alibaba
  • No data24h —
    7d
    —
    30d
    99.99%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    262K
    $/Mtok
    $0.250 / $1.25
    coreweave/fp8fp8

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

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.

Daily availability

One row per endpoint · one dot per day · last 90 days.

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 9 endpoints · 47 days with data, 71 endpoint-days below 90%.

Price changes