modelstatus.dev

DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flashInputtextimageOutputtext

Compare its 63 providersIncident RSSCompare with DeepSeek V4.1 Flash 1017, DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423

CompareDeepSeek V4.1 Flash
  • Healthy24h 100%
    7d
    99.71%
    30d
    99.14%
    p50
    761ms
    p99
    3.86s
    Throughput
    108 tps
    Context
    1.0M
    $/Mtok
    $0.330 / $1.32
    alibaba
  • Healthy24h 100%
    7d
    99.74%
    30d
    99.77%
    p50
    711ms
    p99
    1.32s
    Throughput
    67 tps
    Context
    1.0M
    $/Mtok
    $0.135 / $0.540
    atlas-cloud/fp8fp8
  • Baidu100%
    Healthy24h 100%
    7d
    99.68%
    30d
    99.50%
    p50
    865ms
    p99
    3.70s
    Throughput
    91 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    baidu/fp8fp8
  • Healthy24h 100%
    7d
    99.96%
    30d
    99.87%
    p50
    227ms
    p99
    3.31s
    Throughput
    186 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    baseten
  • Healthy24h 99.80%
    7d
    99.81%
    30d
    99.82%
    p50
    384ms
    p99
    9.35s
    Throughput
    229 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    baseten/us
  • Cohere100%
    Healthy24h 100%
    7d
    99.91%
    30d
    99.79%
    p50
    245ms
    p99
    2.56s
    Throughput
    181 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    cohere
  • Healthy24h 100%
    7d
    98.99%
    30d
    98.63%
    p50
    464ms
    p99
    3.03s
    Throughput
    166 tps
    Context
    1.0M
    $/Mtok
    $0.130 / $0.650
    coreweave/fp8fp8
  • Crusoe100%
    Healthy24h 100%
    7d
    99.93%
    30d
    99.74%
    p50
    517ms
    p99
    2.58s
    Throughput
    145 tps
    Context
    1.0M
    $/Mtok
    $0.290 / $1.20
    crusoe/fp8fp8
  • Decart100%
    Healthy24h 99.29%
    7d
    83.92%
    30d
    95.94%
    p50
    866ms
    p99
    2.05s
    Throughput
    101 tps
    Context
    1.0M
    $/Mtok
    $0.090 / $0.180
    decart/fp4fp4
  • Healthy24h 100%
    7d
    100%
    30d
    99.99%
    p50
    580ms
    p99
    3.63s
    Throughput
    102 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.420
    deepinfra/fp8fp8
  • Healthy24h 100%
    7d
    99.00%
    30d
    96.12%
    p50
    2.37s
    p99
    6.44s
    Throughput
    82 tps
    Context
    1.0M
    $/Mtok
    $0.112 / $0.336
    deepinfra/fp8/flexfp8
  • Healthy24h 100%
    7d
    71.43%
    30d
    73.16%
    p50
    853ms
    p99
    3.31s
    Throughput
    91 tps
    Context
    1.0M
    $/Mtok
    $0.210 / $0.630
    deepinfra/fp8/priorityfp8
  • Healthy24h 100%
    7d
    100%
    30d
    99.88%
    p50
    661ms
    p99
    4.80s
    Throughput
    177 tps
    Context
    1.0M
    $/Mtok
    $0.225 / $0.900
    digitalocean
  • Healthy24h 96.75%
    7d
    97.69%
    30d
    94.61%
    p50
    533ms
    p99
    3.64s
    Throughput
    120 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    fireworks
  • Healthy24h 99.51%
    7d
    99.82%
    30d
    99.88%
    p50
    593ms
    p99
    3.42s
    Throughput
    132 tps
    Context
    1.0M
    $/Mtok
    $0.210 / $0.840
    fireworks/spot
  • Healthy24h 100%
    7d
    100%
    30d
    99.37%
    p50
    287ms
    p99
    1.02s
    Throughput
    358 tps
    Context
    1.0M
    $/Mtok
    $0.450 / $1.80
    fireworks/us
  • Healthy24h 98.90%
    7d
    96.36%
    30d
    98.84%
    p50
    1.56s
    p99
    8.90s
    Throughput
    78 tps
    Context
    1.0M
    $/Mtok
    $0.180 / $0.720
    gmicloud/fp8fp8
  • Healthy24h 100%
    7d
    100%
    30d
    99.97%
    p50
    241ms
    p99
    2.18s
    Throughput
    113 tps
    Context
    1.0M
    $/Mtok
    $0.103 / $0.600
    inference-net/fp8fp8
  • Healthy24h 100%
    7d
    100%
    30d
    99.97%
    p50
    247ms
    p99
    1.70s
    Throughput
    98 tps
    Context
    1.0M
    $/Mtok
    $0.103 / $0.600
    inference-net/usfp8
  • Makora100%
    Healthy24h 99.15%
    7d
    99.60%
    30d
    99.44%
    p50
    247ms
    p99
    2.05s
    Throughput
    160 tps
    Context
    1.0M
    $/Mtok
    $0.260 / $1.17
    makora/fp8fp8
  • Healthy24h 99.85%
    7d
    99.28%
    30d
    95.39%
    p50
    837ms
    p99
    7.23s
    Throughput
    62 tps
    Context
    1.0M
    $/Mtok
    $0.150 / $0.750
    mancer/fp8fp8
  • Modal100%
    Healthy24h 100%
    7d
    99.80%
    30d
    99.94%
    p50
    389ms
    p99
    3.26s
    Throughput
    127 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    modal
  • Morph100%
    Healthy24h 99.86%
    7d
    99.92%
    30d
    99.15%
    p50
    954ms
    p99
    11.1s
    Throughput
    80 tps
    Context
    1.0M
    $/Mtok
    $0.050 / $0.450
    morph/fp8fp8
  • Nebius100%
    Healthy24h 100%
    7d
    99.02%
    30d
    99.03%
    p50
    770ms
    p99
    3.32s
    Throughput
    150 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    nebius/fp8fp8
  • Novita100%
    Healthy24h 100%
    7d
    100%
    30d
    99.26%
    p50
    885ms
    p99
    2.51s
    Throughput
    107 tps
    Context
    1.0M
    $/Mtok
    $0.195 / $0.780
    novita/fp8fp8
  • Healthy24h 99.86%
    7d
    99.91%
    30d
    98.54%
    p50
    566ms
    p99
    17.8s
    Throughput
    109 tps
    Context
    1.0M
    $/Mtok
    $0.035 / $0.500
    open-inference/fp4fp4
  • Healthy24h 100%
    7d
    100%
    30d
    98.85%
    p50
    324ms
    p99
    19.5s
    Throughput
    189 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    parasail/fp8fp8
  • Healthy24h 100%
    7d
    99.99%
    30d
    97.65%
    p50
    806ms
    p99
    5.48s
    Throughput
    168 tps
    Context
    1.0M
    $/Mtok
    $0.156 / $1.20
    primeintellect
  • Reka100%
    Degraded24h 98.39%
    7d
    99.07%
    30d
    97.49%
    p50
    340ms
    p99
    4.07s
    Throughput
    131 tps
    Context
    1.0M
    $/Mtok
    $0.105 / $0.840
    reka
  • Relace100%
    Healthy24h 100%
    7d
    100%
    30d
    100%
    p50
    277ms
    p99
    2.99s
    Throughput
    219 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $0.900
    relace/fastfp4
  • Relace100%
    Healthy24h 99.86%
    7d
    99.95%
    30d
    99.95%
    p50
    924ms
    p99
    21.0s
    Throughput
    140 tps
    Context
    1.0M
    $/Mtok
    $0.035 / $0.500
    relace/fp4fp4
  • Healthy24h 100%
    7d
    100%
    30d
    99.10%
    p50
    896ms
    p99
    3.94s
    Throughput
    86 tps
    Context
    1.0M
    $/Mtok
    $0.090 / $0.250
    sail-research/fp4fp4
  • Healthy24h 100%
    7d
    100%
    30d
    100%
    p50
    940ms
    p99
    3.92s
    Throughput
    86 tps
    Context
    1.0M
    $/Mtok
    $0.090 / $0.250
    sail-research/fp4/usfp4
  • Healthy24h 100%
    7d
    99.95%
    30d
    99.83%
    p50
    1.55s
    p99
    3.65s
    Throughput
    102 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    siliconflow/fp8fp8
  • Healthy24h 100%
    7d
    99.98%
    30d
    99.87%
    p50
    1.72s
    p99
    7.04s
    Throughput
    66 tps
    Context
    1.0M
    $/Mtok
    $0.147 / $0.588
    streamlake/fp8fp8
  • Healthy24h 100%
    7d
    100%
    30d
    99.59%
    p50
    306ms
    p99
    6.59s
    Throughput
    212 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    together
  • Venice100%
    Healthy24h 99.93%
    7d
    99.83%
    30d
    99.71%
    p50
    252ms
    p99
    1.81s
    Throughput
    136 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    venice/fp8fp8
  • Wafer100%
    Healthy24h 100%
    7d
    100%
    30d
    99.98%
    p50
    217ms
    p99
    1.57s
    Throughput
    190 tps
    Context
    1.0M
    $/Mtok
    $0.190 / $0.650
    wafer/mxfp4mxfp4
  • Wafer100%
    Healthy24h 100%
    7d
    100%
    30d
    100%
    p50
    301ms
    p99
    2.97s
    Throughput
    184 tps
    Context
    1.0M
    $/Mtok
    $0.045 / $0.500
    wafer/usmxfp4
  • No data24h —
    7d
    31.95%
    30d
    83.80%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.600 / $2.40
    baseten/fast
  • No data24h —
    7d
    —
    30d
    99.84%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    baseten/fp32fp32
  • No data24h —
    7d
    —
    30d
    99.94%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    baseten/fp8fp8
  • No data24h —
    7d
    —
    30d
    100%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    baseten/fp8/usfp8
  • No data24h —
    7d
    —
    30d
    99.63%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.100 / $0.900
    cloudflare
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    deepinfra/fp4fp4
  • No data24h —
    7d
    —
    30d
    99.24%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.150 / $0.600
    deepseek
  • No data24h —
    7d
    —
    30d
    98.04%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.120 / $1.20
    dekallm
  • No data24h —
    7d
    —
    30d
    100%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.210 / $0.840
    fireworks/flex
  • No data24h 97.24%
    7d
    98.52%
    30d
    97.54%
    p50
    895ms
    p99
    9.83s
    Throughput
    111 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    google-vertex/global
  • No data24h —
    7d
    —
    30d
    99.60%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.070 / $0.300
    inference-net
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.110 / $0.410
    io-net/fp8fp8
  • No data24h —
    7d
    —
    30d
    99.15%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.220 / $0.600
    ionstream
  • Krea—
    No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.225 / $0.900
    krea/fp8fp8
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    makora
  • No data24h —
    7d
    100%
    30d
    96.25%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.170 / $0.670
    modelrun/fp4fp4
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.079 / $0.317
    morph
  • No data24h —
    7d
    —
    30d
    99.96%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.210 / $0.840
    nextbit/fp8fp8
  • No data24h 99.65%
    7d
    96.79%
    30d
    98.51%
    p50
    1.01s
    p99
    7.06s
    Throughput
    84 tps
    Context
    1.0M
    $/Mtok
    $0.210 / $0.840
    phala
  • Reka—
    No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    262K
    $/Mtok
    $0.290 / $1.16
    reka/fp4fp4
  • No data24h —
    7d
    99.98%
    30d
    99.82%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.070 / $0.500
    relace
  • No data24h —
    7d
    65.00%
    30d
    65.00%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.070 / $0.500
    relace/mxfp4mxfp4
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    streamlake
  • No data24h —
    7d
    —
    30d
    99.82%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.100 / $0.650
    wafer

Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

18 endpoints have 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 · 60 endpoints · 54 days with data, 269 endpoint-days below 90%. 3 more not shown.

Price changes