modelstatus.dev

DeepSeek V4 Flash 0423

DeepSeek V4 Flash 0423: providers compared

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

  • Cloudflare100% (best)
    Healthy24h 100%
    7d
    100% (best)
    30d
    100% (best)
    p50
    791ms
    p99
    5.33s
    Throughput
    66 tps
    Context
    384K
    $/Mtok
    $0.440 / $1.32
    cloudflare
  • DeepSeek99.99%
    Healthy24h 98.84%
    7d
    85.42%
    30d
    85.42%
    p50
    766ms
    p99
    6.46s
    Throughput
    87 tps (best)
    Context
    1.0M
    $/Mtok
    $0.220 / $0.660
    deepseek
  • Novita99.96%
    Healthy24h 99.73%
    7d
    99.77%
    30d
    99.77%
    p50
    1.02s
    p99
    6.64s
    Throughput
    76 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    novita/fp8fp8
  • Venice99.95%
    Healthy24h 99.87%
    7d
    99.52%
    30d
    99.52%
    p50
    1.63s
    p99
    5.08s
    Throughput
    31 tps
    Context
    1.0M
    $/Mtok
    $0.138 / $0.275
    venice
  • Alibaba99.92%
    Healthy24h 99.74%
    7d
    99.71%
    30d
    99.71%
    p50
    840ms
    p99
    5.25s
    Throughput
    57 tps
    Context
    1.0M
    $/Mtok
    $0.134 / $0.268
    alibaba/fp8fp8
  • GMICloud99.92%
    Healthy24h 99.68%
    7d
    99.39%
    30d
    99.39%
    p50
    2.43s
    p99
    10.6s
    Throughput
    46 tps
    Context
    1.0M
    $/Mtok
    $0.084 / $0.168
    gmicloud/fp8fp8
  • Baidu99.90%
    Healthy24h 98.59%
    7d
    98.67%
    30d
    98.67%
    p50
    691ms
    p99
    6.31s
    Throughput
    82 tps
    Context
    1.0M
    $/Mtok
    $0.081 / $0.162
    baidu/fp8fp8
  • DeepInfra99.81%
    Healthy24h 99.66%
    7d
    99.30%
    30d
    99.30%
    p50
    766ms
    p99
    2.64s (best)
    Throughput
    28 tps
    Context
    1.0M
    $/Mtok
    $0.090 / $0.180
    deepinfra/fp8fp8
  • Healthy24h 99.81%
    7d
    99.89%
    30d
    99.89%
    p50
    1.05s
    p99
    5.10s
    Throughput
    48 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    atlas-cloud/fp4fp4
  • Healthy24h 99.74%
    7d
    99.23%
    30d
    99.23%
    p50
    3.51s
    p99
    12.3s
    Throughput
    34 tps
    Context
    1.0M
    $/Mtok
    $0.081 / $0.162
    streamlake/fp8fp8
  • Parasail99.53%
    Healthy24h 99.55%
    7d
    99.32%
    30d
    99.32%
    p50
    758ms
    p99
    8.03s
    Throughput
    52 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    parasail/fp8fp8
  • Healthy24h 99.22%
    7d
    99.03%
    30d
    99.03%
    p50
    1.23s
    p99
    11.9s
    Throughput
    59 tps
    Context
    1.0M
    $/Mtok
    $0.130 / $0.280
    siliconflow/fp8fp8
  • Healthy24h 99.70%
    7d
    99.70%
    30d
    99.70%
    p50
    821ms
    p99
    10.6s
    Throughput
    19 tps
    Context
    1.0M
    $/Mtok
    $0.090 / $0.180
    sail-research/fp4fp4
  • Healthy24h 99.31%
    7d
    98.84%
    30d
    98.84%
    p50
    1.69s
    p99
    26.7s
    Throughput
    6.0 tps
    Context
    1.0M
    $/Mtok
    $0.068 / $0.168 (best)
    digitalocean
  • CoreWeave98.89%
    Healthy24h 99.51%
    7d
    99.57%
    30d
    99.57%
    p50
    531ms (best)
    p99
    12.3s
    Throughput
    37 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    coreweave/fp8fp8
  • Phala97.08%
    Healthy24h 92.00%
    7d
    95.37%
    30d
    95.37%
    p50
    4.44s
    p99
    32.3s
    Throughput
    8.0 tps
    Context
    1.0M
    $/Mtok
    $0.200 / $0.400
    phala
  • Mancer 296.65%
    Healthy24h 98.60%
    7d
    98.70%
    30d
    98.70%
    p50
    1.22s
    p99
    10.3s
    Throughput
    26 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.450
    mancer/fp8fp8
  • Azure91.67%
    Degraded24h 89.10%
    7d
    85.64%
    30d
    85.64%
    p50
    1.81s
    p99
    21.1s
    Throughput
    30 tps
    Context
    1.0M
    $/Mtok
    $0.210 / $0.560
    azure/us

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.