modelstatus.dev

Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B: providers compared

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

  • Modal100% (best)
    Healthy24h 99.35%
    7d
    99.15%
    30d
    99.15%
    p50
    876ms (best)
    p99
    7.23s
    Throughput
    90 tps
    Context
    1.0M
    $/Mtok
    $2.00 / $6.00 (best)
    modal/nvfp4nvfp4
  • SiliconFlow100% (best)
    Healthy24h 99.94%
    7d
    99.81%
    30d
    99.81%
    p50
    3.68s
    p99
    27.9s
    Throughput
    34 tps
    Context
    1.0M
    $/Mtok
    $2.00 / $6.00 (best)
    siliconflow/fp8fp8
  • DeepInfra96.12%
    Healthy24h 96.26%
    7d
    95.91%
    30d
    95.91%
    p50
    1.17s
    p99
    9.11s
    Throughput
    25 tps
    Context
    262K
    $/Mtok
    $2.00 / $6.00 (best)
    deepinfra/fp4fp4
  • No data24h 100%
    7d
    100% (best)
    30d
    100% (best)
    p50
    1.23s
    p99
    15.0s
    Throughput
    45 tps
    Context
    1.0M
    $/Mtok
    $2.00 / $6.00 (best)
    alibaba
  • No data24h 89.81%
    7d
    98.68%
    30d
    98.68%
    p50
    1.65s
    p99
    11.9s
    Throughput
    25 tps
    Context
    262K
    $/Mtok
    $2.00 / $6.00 (best)
    digitalocean
  • No data24h 99.98%
    7d
    99.83%
    30d
    99.83%
    p50
    991ms
    p99
    3.06s (best)
    Throughput
    168 tps (best)
    Context
    1.0M
    $/Mtok
    $2.50 / $6.25
    together
  • No data24h 99.56%
    7d
    98.46%
    30d
    98.46%
    p50
    1.16s
    p99
    11.7s
    Throughput
    103 tps
    Context
    262K
    $/Mtok
    $2.50 / $7.50
    venice

Measured 1m 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, averaged over the hour.

Throughput

Median tokens per second.