modelstatus.dev

Qwen3.8 27B

Qwen3.8 27B: providers compared

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

  • Reka100% (best)
    Healthy24h 99.84%
    7d
    99.53%
    30d
    99.53%
    p50
    1.55s
    p99
    15.1s
    Throughput
    55 tps
    Context
    262K
    $/Mtok
    $0.450 / $3.20
    reka/fp8fp8
  • Venice100% (best)
    Healthy24h 99.82%
    7d
    99.26%
    30d
    99.26%
    p50
    1.17s
    p99
    12.4s
    Throughput
    92 tps (best)
    Context
    262K
    $/Mtok
    $0.450 / $3.20
    venice/fp8fp8
  • AkashML99.57%
    Healthy24h 97.97%
    7d
    98.59%
    30d
    98.59%
    p50
    1.83s
    p99
    36.2s
    Throughput
    33 tps
    Context
    262K
    $/Mtok
    $0.450 / $3.20
    akashml/bf16bf16
  • Parasail98.70%
    Healthy24h 98.93%
    7d
    98.39%
    30d
    98.39%
    p50
    1.39s
    p99
    26.7s
    Throughput
    25 tps
    Context
    262K
    $/Mtok
    $0.450 / $3.20
    parasail/fp8fp8
  • Io Net98.55%
    Healthy24h 98.59%
    7d
    99.14%
    30d
    99.14%
    p50
    1.09s (best)
    p99
    8.02s (best)
    Throughput
    11 tps
    Context
    66K
    $/Mtok
    $0.480 / $3.40
    io-net/fp8fp8
  • Alibaba97.83%
    Healthy24h 99.92%
    7d
    99.86% (best)
    30d
    99.86% (best)
    p50
    2.19s
    p99
    89.7s
    Throughput
    45 tps
    Context
    1.0M
    $/Mtok
    $0.575 / $3.45
    alibaba
  • Chutes97.63%
    Healthy24h 97.48%
    7d
    97.68%
    30d
    97.68%
    p50
    5.60s
    p99
    50.7s
    Throughput
    13 tps
    Context
    262K
    $/Mtok
    $0.400 / $3.00 (best)
    chutes/fp8fp8

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.