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
  • Degraded24h 92.28%
    7d
    96.48%
    30d
    96.48%
    p50
    1.39s
    p99
    6.72s
    Throughput
    43 tps
    Context
    1.0M
    $/Mtok
    $1.68 / $3.38
    atlas-cloud/fp4fp4
  • Baidu100%
    Degraded24h 98.55%
    7d
    97.92%
    30d
    97.92%
    p50
    1.05s
    p99
    3.09s
    Throughput
    47 tps
    Context
    1.0M
    $/Mtok
    $1.69 / $3.38
    baidu/fp8fp8
  • Healthy24h 99.88%
    7d
    99.88%
    30d
    99.88%
    p50
    431ms
    p99
    3.11s
    Throughput
    51 tps
    Context
    1.0M
    $/Mtok
    $1.74 / $3.48
    baseten/fp4fp4
  • Degraded24h 95.83%
    7d
    99.50%
    30d
    99.50%
    p50
    571ms
    p99
    3.77s
    Throughput
    57 tps
    Context
    1.0M
    $/Mtok
    $1.15 / $2.55
    coreweave/fp8fp8
  • Healthy24h 99.45%
    7d
    98.58%
    30d
    98.58%
    p50
    1.08s
    p99
    22.4s
    Throughput
    30 tps
    Context
    1.0M
    $/Mtok
    $1.30 / $2.60
    deepinfra/fp8fp8
  • Healthy24h 99.47%
    7d
    84.27%
    30d
    84.27%
    p50
    1.03s
    p99
    3.09s
    Throughput
    33 tps
    Context
    1.0M
    $/Mtok
    $1.32 / $3.96
    deepseek
  • Alibaba99.86%
    Degraded24h 95.95%
    7d
    98.22%
    30d
    98.22%
    p50
    1.50s
    p99
    5.29s
    Throughput
    52 tps
    Context
    1.0M
    $/Mtok
    $1.42 / $2.83
    alibaba/fp8fp8
  • Healthy24h 98.57%
    7d
    98.21%
    30d
    98.21%
    p50
    2.21s
    p99
    14.5s
    Throughput
    38 tps
    Context
    1.0M
    $/Mtok
    $0.790 / $1.58
    streamlake/fp8fp8
  • GMICloud99.63%
    Degraded24h 94.14%
    7d
    96.85%
    30d
    96.85%
    p50
    3.27s
    p99
    12.2s
    Throughput
    29 tps
    Context
    1.0M
    $/Mtok
    $0.792 / $2.38
    gmicloud/fp8fp8
  • Novita99.41%
    Healthy24h 98.57%
    7d
    99.05%
    30d
    99.05%
    p50
    1.48s
    p99
    82.0s
    Throughput
    54 tps
    Context
    1.0M
    $/Mtok
    $1.60 / $3.20
    novita/fp8fp8
  • Degraded24h 96.41%
    7d
    97.17%
    30d
    97.17%
    p50
    2.11s
    p99
    107s
    Throughput
    42 tps
    Context
    1.0M
    $/Mtok
    $1.50 / $3.14
    siliconflow/fp8fp8
  • Parasail98.15%
    Degraded24h 91.24%
    7d
    91.97%
    30d
    91.97%
    p50
    783ms
    p99
    8.16s
    Throughput
    48 tps
    Context
    1.0M
    $/Mtok
    $1.74 / $3.48
    parasail/fp8fp8
  • Together97.03%
    Healthy24h 96.11%
    7d
    97.54%
    30d
    97.54%
    p50
    951ms
    p99
    13.8s
    Throughput
    45 tps
    Context
    512K
    $/Mtok
    $1.74 / $3.48
    together
  • Ionstream96.93%
    Degraded24h 94.35%
    7d
    95.81%
    30d
    95.81%
    p50
    2.71s
    p99
    15.6s
    Throughput
    20 tps
    Context
    1.0M
    $/Mtok
    $1.13 / $2.26
    ionstream/fp4fp4
  • Venice96.19%
    Healthy24h 79.36%
    7d
    84.46%
    30d
    84.46%
    p50
    2.08s
    p99
    30.3s
    Throughput
    42 tps
    Context
    1.0M
    $/Mtok
    $1.65 / $3.30
    venice
  • Azure96.03%
    Degraded24h 93.19%
    7d
    94.63%
    30d
    94.63%
    p50
    2.54s
    p99
    18.3s
    Throughput
    45 tps
    Context
    1.0M
    $/Mtok
    $1.91 / $3.83
    azure/us
  • Fireworks95.21%
    Degraded24h 93.97%
    7d
    95.75%
    30d
    95.75%
    p50
    1.43s
    p99
    9.65s
    Throughput
    56 tps
    Context
    1.0M
    $/Mtok
    $1.74 / $3.48
    fireworks
  • Degraded24h 91.62%
    7d
    55.59%
    30d
    55.59%
    p50
    2.69s
    p99
    17.4s
    Throughput
    5.0 tps
    Context
    1.0M
    $/Mtok
    $0.870 / $1.74
    digitalocean

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

Price changes

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.