modelstatus.dev

DeepSeek V4 Pro 0423

deepseek/deepseek-v4-proInputtextOutputtext

Compare its 21 providersIncident RSSCompare with DeepSeek V4 Pro 0813, DeepSeek V4 Pro 0813 (batch), DeepSeek V4 Flash 0731

CompareDeepSeek V4 Pro 0423
  • Healthy24h 99.98%
    7d
    99.90%
    30d
    99.79%
    p50
    1.66s
    p99
    3.59s
    Throughput
    45 tps
    Context
    1.0M
    $/Mtok
    $1.42 / $2.83
    alibaba/fp8fp8
  • Healthy24h 99.97%
    7d
    99.06%
    30d
    98.59%
    p50
    1.32s
    p99
    7.15s
    Throughput
    39 tps
    Context
    1.0M
    $/Mtok
    $1.68 / $3.38
    atlas-cloud/fp4fp4
  • Baidu100%
    Healthy24h 99.90%
    7d
    99.59%
    30d
    99.11%
    p50
    1.03s
    p99
    6.19s
    Throughput
    53 tps
    Context
    1.0M
    $/Mtok
    $0.906 / $1.81
    baidu/fp8fp8
  • Healthy24h 99.45%
    7d
    99.61%
    30d
    99.53%
    p50
    585ms
    p99
    8.00s
    Throughput
    88 tps
    Context
    1.0M
    $/Mtok
    $1.74 / $3.48
    baseten/fp4fp4
  • Healthy24h 97.65%
    7d
    92.67%
    30d
    92.67%
    p50
    1.31s
    p99
    50.9s
    Throughput
    40 tps
    Context
    1.0M
    $/Mtok
    $1.15 / $2.55
    cloudflare
  • Healthy24h 99.98%
    7d
    99.31%
    30d
    95.27%
    p50
    666ms
    p99
    6.37s
    Throughput
    38 tps
    Context
    1.0M
    $/Mtok
    $1.04 / $2.09
    digitalocean
  • Healthy24h 98.50%
    7d
    98.43%
    30d
    98.28%
    p50
    2.18s
    p99
    6.17s
    Throughput
    28 tps
    Context
    1.0M
    $/Mtok
    $0.957 / $1.91
    gmicloud/fp8fp8
  • Novita100%
    Healthy24h 99.99%
    7d
    99.86%
    30d
    99.84%
    p50
    1.64s
    p99
    5.33s
    Throughput
    97 tps
    Context
    1.0M
    $/Mtok
    $1.60 / $3.20
    novita/fp8fp8
  • Healthy24h 99.74%
    7d
    99.43%
    30d
    97.88%
    p50
    696ms
    p99
    17.3s
    Throughput
    42 tps
    Context
    1.0M
    $/Mtok
    $1.74 / $3.48
    parasail/fp8fp8
  • Azure99.84%
    Healthy24h 99.13%
    7d
    99.04%
    30d
    98.59%
    p50
    2.02s
    p99
    22.3s
    Throughput
    34 tps
    Context
    1.0M
    $/Mtok
    $1.91 / $3.83
    azure/us
  • Venice99.83%
    Healthy24h 90.81%
    7d
    94.81%
    30d
    94.78%
    p50
    1.87s
    p99
    13.2s
    Throughput
    38 tps
    Context
    1.0M
    $/Mtok
    $1.65 / $3.30
    venice
  • Healthy24h 99.63%
    7d
    96.69%
    30d
    98.33%
    p50
    1.73s
    p99
    7.76s
    Throughput
    46 tps
    Context
    1.0M
    $/Mtok
    $1.50 / $3.14
    siliconflow/fp8fp8
  • Healthy24h 99.42%
    7d
    98.11%
    30d
    98.68%
    p50
    1.80s
    p99
    28.4s
    Throughput
    41 tps
    Context
    1.0M
    $/Mtok
    $0.907 / $1.81
    streamlake/fp8fp8
  • DeepInfra98.70%
    Healthy24h 99.49%
    7d
    99.11%
    30d
    99.19%
    p50
    1.47s
    p99
    7.89s
    Throughput
    22 tps
    Context
    1.0M
    $/Mtok
    $1.30 / $2.60
    deepinfra/fp8fp8
  • NextBit98.51%
    Healthy24h 99.32%
    7d
    99.73%
    30d
    98.69%
    p50
    2.01s
    p99
    3.75s
    Throughput
    46 tps
    Context
    1.0M
    $/Mtok
    $1.91 / $3.83
    nextbit/fp8fp8
  • No data24h
    7d
    30d
    99.80%
    p50
    p99
    Throughput
    Context
    1.0M
    $/Mtok
    $1.15 / $2.55
    coreweave/fp8fp8
  • No data24h
    7d
    30d
    p50
    p99
    Throughput
    Context
    1.0M
    $/Mtok
    $1.74 / $3.48
    crusoe/fp8fp8
  • No data24h
    7d
    30d
    86.30%
    p50
    p99
    Throughput
    Context
    1.0M
    $/Mtok
    $0.660 / $1.98
    deepseek
  • No data24h
    7d
    0.00%
    30d
    11.25%
    p50
    p99
    Throughput
    Context
    1.0M
    $/Mtok
    $1.20 / $1.20
    fireworks
  • No data24h
    7d
    30d
    98.82%
    p50
    p99
    Throughput
    Context
    1.0M
    $/Mtok
    $1.13 / $2.26
    ionstream/fp4fp4
  • No data24h
    7d
    30d
    98.22%
    p50
    p99
    Throughput
    Context
    512K
    $/Mtok
    $1.74 / $3.48
    together

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

1 endpoint has no chartable data in this range.

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.

Daily availability

One row per endpoint · one dot per day · last 90 days.

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 20 endpoints · 30 days with data, 134 endpoint-days below 90%.

Price changes