modelstatus.dev

DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813InputtextOutputtext

Compare its 28 providersIncident RSSCompare with DeepSeek V4 Pro 0423, DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423

CompareDeepSeek V4 Pro 0813
  • Healthy24h 98.83%
    7d
    98.85%
    30d
    99.39%
    p50
    1.41s
    p99
    6.96s
    Throughput
    66 tps
    Context
    1.0M
    $/Mtok
    $1.32 / $3.96
    atlas-cloud/fp8fp8
  • Baidu100%
    Healthy24h 99.96%
    7d
    99.92%
    30d
    99.92%
    p50
    1.01s
    p99
    4.29s
    Throughput
    53 tps
    Context
    1.0M
    $/Mtok
    $1.32 / $3.96
    baidu/fp8fp8
  • Healthy24h 99.91%
    7d
    99.69%
    30d
    99.69%
    p50
    599ms
    p99
    3.50s
    Throughput
    123 tps
    Context
    1.0M
    $/Mtok
    $1.31 / $3.96
    coreweave/fp8fp8
  • Healthy24h 99.99%
    7d
    99.96%
    30d
    99.97%
    p50
    1.19s
    p99
    31.3s
    Throughput
    62 tps
    Context
    1.0M
    $/Mtok
    $1.32 / $3.96
    deepseek
  • Healthy24h 99.95%
    7d
    99.89%
    30d
    99.69%
    p50
    419ms
    p99
    3.90s
    Throughput
    31 tps
    Context
    1.0M
    $/Mtok
    $1.32 / $3.96
    digitalocean
  • Healthy24h 99.93%
    7d
    99.94%
    30d
    99.77%
    p50
    3.56s
    p99
    7.90s
    Throughput
    34 tps
    Context
    1.0M
    $/Mtok
    $1.06 / $3.17
    gmicloud/fp8fp8
  • Healthy24h 99.84%
    7d
    97.97%
    30d
    98.91%
    p50
    1.86s
    p99
    8.87s
    Throughput
    24 tps
    Context
    1.0M
    $/Mtok
    $0.238 / $1.98
    ionstream
  • Novita100%
    Healthy24h 99.97%
    7d
    99.97%
    30d
    99.92%
    p50
    1.34s
    p99
    14.1s
    Throughput
    83 tps
    Context
    1.0M
    $/Mtok
    $0.990 / $2.97
    novita/fp8fp8
  • Healthy24h 99.71%
    7d
    99.07%
    30d
    99.53%
    p50
    1.13s
    p99
    22.2s
    Throughput
    33 tps
    Context
    1.0M
    $/Mtok
    $1.32 / $3.96
    parasail/fp8fp8
  • Phala100%
    Healthy24h 99.52%
    7d
    99.35%
    30d
    99.06%
    p50
    2.23s
    p99
    5.62s
    Throughput
    69 tps
    Context
    1.0M
    $/Mtok
    $1.45 / $4.36
    phala
  • Relace100%
    Healthy24h 99.94%
    7d
    98.48%
    30d
    98.48%
    p50
    861ms
    p99
    6.39s
    Throughput
    95 tps
    Context
    1.0M
    $/Mtok
    $0.190 / $4.20
    relace/fp4fp4
  • Healthy24h 99.99%
    7d
    100%
    30d
    99.18%
    p50
    1.42s
    p99
    20.5s
    Throughput
    80 tps
    Context
    1.0M
    $/Mtok
    $1.32 / $3.96
    siliconflow/fp8fp8
  • Wafer100%
    Healthy24h 97.23%
    7d
    99.15%
    30d
    99.17%
    p50
    462ms
    p99
    2.85s
    Throughput
    67 tps
    Context
    1.0M
    $/Mtok
    $0.850 / $5.00
    wafer
  • Healthy24h 99.74%
    7d
    99.61%
    30d
    99.71%
    p50
    2.29s
    p99
    11.8s
    Throughput
    46 tps
    Context
    1.0M
    $/Mtok
    $0.849 / $2.55
    streamlake
  • NextBit99.61%
    Healthy24h 99.88%
    7d
    99.94%
    30d
    99.47%
    p50
    2.62s
    p99
    6.49s
    Throughput
    57 tps
    Context
    1.0M
    $/Mtok
    $1.06 / $3.17
    nextbit/fp8fp8
  • Healthy24h 97.54%
    7d
    99.20%
    30d
    98.30%
    p50
    950ms
    p99
    6.63s
    Throughput
    45 tps
    Context
    1.0M
    $/Mtok
    $1.32 / $3.96
    cloudflare
  • Alibaba98.66%
    Healthy24h 99.05%
    7d
    98.40%
    30d
    99.41%
    p50
    1.13s
    p99
    2.25s
    Throughput
    73 tps
    Context
    1.0M
    $/Mtok
    $1.12 / $3.37
    alibaba
  • Together98.65%
    Healthy24h 98.54%
    7d
    98.24%
    30d
    99.12%
    p50
    918ms
    p99
    5.87s
    Throughput
    64 tps
    Context
    1.0M
    $/Mtok
    $1.32 / $3.96
    together
  • No data24h —
    7d
    —
    30d
    98.94%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $1.32 / $3.96
    baseten/fp4fp4
  • No data24h 98.59%
    7d
    99.56%
    30d
    99.26%
    p50
    1.56s
    p99
    9.81s
    Throughput
    49 tps
    Context
    1.0M
    $/Mtok
    $1.30 / $2.60
    deepinfra/fp8fp8
  • No data24h —
    7d
    0.00%
    30d
    96.35%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $1.32 / $3.96
    fireworks
  • No data24h —
    7d
    99.59%
    30d
    99.59%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    262K
    $/Mtok
    $0.490 / $2.45
    io-net/fp8fp8
  • No data24h —
    7d
    —
    30d
    99.94%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $1.10 / $3.30
    ionstream/fp4fp4
  • No data24h —
    7d
    —
    30d
    86.13%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    979K
    $/Mtok
    $1.32 / $3.96
    nebius/fp8fp8
  • Reka—
    No data24h —
    7d
    99.51%
    30d
    99.51%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $1.12 / $3.37
    reka
  • No data24h —
    7d
    99.14%
    30d
    99.40%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.400 / $4.30
    sail-research/fp4fp4
  • No data24h —
    7d
    99.18%
    30d
    99.09%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.400 / $4.30
    sail-research/usfp4
  • Down24h 93.91%
    7d
    95.60%
    30d
    97.78%
    p50
    2.06s
    p99
    15.0s
    Throughput
    32 tps
    Context
    1.0M
    $/Mtok
    $1.65 / $4.95
    venice

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

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 · 28 endpoints · 48 days with data, 110 endpoint-days below 90%.

Price changes