modelstatus.dev

DeepSeek V4 Pro 0423

deepseek/deepseek-v4-pro

Compare with DeepSeek V4 Pro 0813, DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423

CompareDeepSeek V4 Pro 0423
  • Healthy24h 99.88%
    7d
    99.88%
    30d
    99.88%
    p50
    420ms
    p99
    2.14s
    Throughput
    55 tps
    Context
    1.0M
    $/Mtok
    $1.74 / $3.48
    baseten/fp4fp4
  • Healthy24h 99.47%
    7d
    84.57%
    30d
    84.57%
    p50
    1.01s
    p99
    3.03s
    Throughput
    37 tps
    Context
    1.0M
    $/Mtok
    $1.32 / $3.96
    deepseek
  • Novita100%
    Healthy24h 98.58%
    7d
    99.07%
    30d
    99.07%
    p50
    1.44s
    p99
    11.9s
    Throughput
    58 tps
    Context
    1.0M
    $/Mtok
    $1.60 / $3.20
    novita/fp8fp8
  • Healthy24h 91.64%
    7d
    92.07%
    30d
    92.07%
    p50
    615ms
    p99
    6.59s
    Throughput
    56 tps
    Context
    1.0M
    $/Mtok
    $1.74 / $3.48
    parasail/fp8fp8
  • Healthy24h 96.69%
    7d
    97.19%
    30d
    97.19%
    p50
    2.19s
    p99
    16.2s
    Throughput
    41 tps
    Context
    1.0M
    $/Mtok
    $1.50 / $3.14
    siliconflow/fp8fp8
  • Ionstream99.83%
    Healthy24h 94.56%
    7d
    95.81%
    30d
    95.81%
    p50
    2.47s
    p99
    17.2s
    Throughput
    24 tps
    Context
    1.0M
    $/Mtok
    $1.13 / $2.26
    ionstream/fp4fp4
  • Healthy24h 98.66%
    7d
    98.23%
    30d
    98.23%
    p50
    2.21s
    p99
    14.0s
    Throughput
    38 tps
    Context
    1.0M
    $/Mtok
    $0.790 / $1.58
    streamlake/fp8fp8
  • Healthy24h 91.97%
    7d
    56.61%
    30d
    56.61%
    p50
    2.44s
    p99
    34.1s
    Throughput
    10 tps
    Context
    1.0M
    $/Mtok
    $0.870 / $1.74
    digitalocean
  • Healthy24h 92.89%
    7d
    96.49%
    30d
    96.49%
    p50
    1.35s
    p99
    4.14s
    Throughput
    44 tps
    Context
    1.0M
    $/Mtok
    $1.68 / $3.38
    atlas-cloud/fp4fp4
  • Alibaba99.48%
    Healthy24h 96.25%
    7d
    98.23%
    30d
    98.23%
    p50
    1.37s
    p99
    4.28s
    Throughput
    56 tps
    Context
    1.0M
    $/Mtok
    $1.42 / $2.83
    alibaba/fp8fp8
  • Venice99.43%
    Healthy24h 80.02%
    7d
    84.60%
    30d
    84.60%
    p50
    2.05s
    p99
    14.7s
    Throughput
    40 tps
    Context
    1.0M
    $/Mtok
    $1.65 / $3.30
    venice
  • Baidu99.12%
    Healthy24h 98.61%
    7d
    97.90%
    30d
    97.90%
    p50
    1.04s
    p99
    3.93s
    Throughput
    46 tps
    Context
    1.0M
    $/Mtok
    $1.69 / $3.38
    baidu/fp8fp8
  • GMICloud99.02%
    Healthy24h 94.52%
    7d
    96.85%
    30d
    96.85%
    p50
    3.03s
    p99
    10.1s
    Throughput
    32 tps
    Context
    1.0M
    $/Mtok
    $0.792 / $2.38
    gmicloud/fp8fp8
  • Together98.78%
    Healthy24h 96.17%
    7d
    97.54%
    30d
    97.54%
    p50
    721ms
    p99
    8.04s
    Throughput
    52 tps
    Context
    512K
    $/Mtok
    $1.74 / $3.48
    together
  • Azure96.99%
    Healthy24h 93.51%
    7d
    94.62%
    30d
    94.62%
    p50
    2.04s
    p99
    21.9s
    Throughput
    49 tps
    Context
    1.0M
    $/Mtok
    $1.91 / $3.83
    azure/us
  • No data24h 96.08%
    7d
    99.51%
    30d
    99.51%
    p50
    566ms
    p99
    12.9s
    Throughput
    58 tps
    Context
    1.0M
    $/Mtok
    $1.15 / $2.55
    coreweave/fp8fp8
  • No data24h 99.46%
    7d
    98.59%
    30d
    98.59%
    p50
    1.04s
    p99
    14.4s
    Throughput
    22 tps
    Context
    1.0M
    $/Mtok
    $1.30 / $2.60
    deepinfra/fp8fp8
  • No data24h 94.11%
    7d
    95.80%
    30d
    95.80%
    p50
    1.35s
    p99
    5.56s
    Throughput
    68 tps
    Context
    1.0M
    $/Mtok
    $1.74 / $3.48
    fireworks

Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

Price changes

3 endpoints reporting no data are omitted from the charts.

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.