modelstatus.dev

Qwen3.6 35B A3B

Qwen3.6 35B A3B: providers compared

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

  • AkashML100% (best)
    Healthy24h 99.38%
    7d
    99.68%
    30d
    99.68%
    p50
    597ms
    p99
    2.80s
    Throughput
    77 tps
    Context
    262K
    $/Mtok
    $0.140 / $1.00
    akashml/fp8fp8
  • CoreWeave100% (best)
    Degraded24h 99.34%
    7d
    99.69%
    30d
    99.69%
    p50
    428ms (best)
    p99
    5.53s
    Throughput
    135 tps
    Context
    262K
    $/Mtok
    $0.250 / $1.25
    coreweave/fp8fp8
  • DeepInfra100% (best)
    Healthy24h 97.81%
    7d
    93.80%
    30d
    93.80%
    p50
    662ms
    p99
    19.7s
    Throughput
    56 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.950
    deepinfra/fp8fp8
  • Io Net100% (best)
    Healthy24h 99.45%
    7d
    99.39%
    30d
    99.39%
    p50
    1.48s
    p99
    34.4s
    Throughput
    123 tps
    Context
    262K
    $/Mtok
    $0.190 / $1.19
    io-net/fp8fp8
  • SiliconFlow100% (best)
    Healthy24h 97.04%
    7d
    97.98%
    30d
    97.98%
    p50
    1.84s
    p99
    15.2s
    Throughput
    75 tps
    Context
    262K
    $/Mtok
    $0.200 / $1.60
    siliconflow/fp8fp8
  • Parasail99.90%
    Healthy24h 98.77%
    7d
    99.19%
    30d
    99.19%
    p50
    564ms
    p99
    5.54s
    Throughput
    51 tps
    Context
    262K
    $/Mtok
    $0.150 / $1.00
    parasail/fp8fp8
  • Venice97.30%
    Healthy24h 99.66%
    7d
    99.87% (best)
    30d
    99.87% (best)
    p50
    627ms
    p99
    2.07s (best)
    Throughput
    158 tps (best)
    Context
    256K
    $/Mtok
    $0.100 / $1.00
    venice/fp8fp8
  • Phala96.88%
    Healthy24h 96.68%
    7d
    98.18%
    30d
    98.18%
    p50
    1.39s
    p99
    8.94s
    Throughput
    102 tps
    Context
    262K
    $/Mtok
    $0.200 / $1.27
    phala
  • Darkbloom90.42%
    Degraded24h 86.90%
    7d
    87.94%
    30d
    87.94%
    p50
    5.31s
    p99
    22.9s
    Throughput
    39 tps
    Context
    262K
    $/Mtok
    $0.080 / $0.750 (best)
    darkbloom/fp4fp4
  • Down24h 98.88%
    7d
    99.41%
    30d
    99.41%
    p50
    1.07s
    p99
    7.36s
    Throughput
    103 tps
    Context
    262K
    $/Mtok
    $0.186 / $1.11
    atlas-cloud/fp8fp8
  • No data24h
    7d
    69.81%
    30d
    69.81%
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.080 / $0.750 (best)
    darkbloom

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.

Throughput

Median tokens per second.