modelstatus.dev

DeepSeek V4 Flash 0423

DeepSeek V4 Flash 0423: providers compared

Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.

  • Cloudflare100% (best)
    Healthy24h 100%
    7d
    100% (best)
    30d
    100% (best)
    p50
    794ms
    p99
    7.17s
    Throughput
    62 tps
    Context
    384K
    $/Mtok
    $0.440 / $1.32
    cloudflare
  • DeepSeek99.99%
    Healthy24h 98.82%
    7d
    85.66%
    30d
    85.66%
    p50
    1.08s
    p99
    10.1s
    Throughput
    78 tps (best)
    Context
    1.0M
    $/Mtok
    $0.220 / $0.660
    deepseek
  • Novita99.96%
    Healthy24h 99.72%
    7d
    99.78%
    30d
    99.78%
    p50
    1.10s
    p99
    9.04s
    Throughput
    69 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    novita/fp8fp8
  • Healthy24h 99.81%
    7d
    99.89%
    30d
    99.89%
    p50
    1.04s
    p99
    6.23s
    Throughput
    44 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    atlas-cloud/fp4fp4
  • Alibaba99.93%
    Healthy24h 99.74%
    7d
    99.71%
    30d
    99.71%
    p50
    841ms
    p99
    3.91s
    Throughput
    57 tps
    Context
    1.0M
    $/Mtok
    $0.134 / $0.268
    alibaba/fp8fp8
  • Parasail99.83%
    Healthy24h 99.56%
    7d
    99.32%
    30d
    99.32%
    p50
    688ms (best)
    p99
    5.36s
    Throughput
    70 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    parasail/fp8fp8
  • Healthy24h 99.74%
    7d
    99.24%
    30d
    99.24%
    p50
    3.05s
    p99
    12.8s
    Throughput
    34 tps
    Context
    1.0M
    $/Mtok
    $0.081 / $0.162
    streamlake/fp8fp8
  • Healthy24h 99.14%
    7d
    99.04%
    30d
    99.04%
    p50
    1.60s
    p99
    14.5s
    Throughput
    59 tps
    Context
    1.0M
    $/Mtok
    $0.130 / $0.280
    siliconflow/fp8fp8
  • Venice99.65%
    Healthy24h 99.87%
    7d
    99.53%
    30d
    99.53%
    p50
    1.64s
    p99
    6.16s
    Throughput
    29 tps
    Context
    1.0M
    $/Mtok
    $0.138 / $0.275
    venice
  • DeepInfra99.50%
    Healthy24h 99.66%
    7d
    99.31%
    30d
    99.31%
    p50
    778ms
    p99
    3.47s (best)
    Throughput
    27 tps
    Context
    1.0M
    $/Mtok
    $0.090 / $0.180
    deepinfra/fp8fp8
  • Healthy24h 99.69%
    7d
    99.70%
    30d
    99.70%
    p50
    798ms
    p99
    9.70s
    Throughput
    21 tps
    Context
    1.0M
    $/Mtok
    $0.090 / $0.180
    sail-research/fp4fp4
  • Baidu99.43%
    Degraded24h 98.33%
    7d
    98.57%
    30d
    98.57%
    p50
    951ms
    p99
    17.8s
    Throughput
    71 tps
    Context
    1.0M
    $/Mtok
    $0.081 / $0.162
    baidu/fp8fp8
  • Mancer 299.21%
    Healthy24h 98.58%
    7d
    98.67%
    30d
    98.67%
    p50
    1.17s
    p99
    9.70s
    Throughput
    28 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.450
    mancer/fp8fp8
  • CoreWeave99.19%
    Healthy24h 99.51%
    7d
    99.57%
    30d
    99.57%
    p50
    709ms
    p99
    16.0s
    Throughput
    33 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    coreweave/fp8fp8
  • GMICloud98.98%
    Healthy24h 99.67%
    7d
    99.40%
    30d
    99.40%
    p50
    2.44s
    p99
    12.6s
    Throughput
    46 tps
    Context
    1.0M
    $/Mtok
    $0.084 / $0.168
    gmicloud/fp8fp8
  • Phala98.52%
    Healthy24h 91.99%
    7d
    95.41%
    30d
    95.41%
    p50
    4.63s
    p99
    63.0s
    Throughput
    7.0 tps
    Context
    1.0M
    $/Mtok
    $0.200 / $0.400
    phala
  • Healthy24h 99.30%
    7d
    98.85%
    30d
    98.85%
    p50
    1.94s
    p99
    37.9s
    Throughput
    5.0 tps
    Context
    1.0M
    $/Mtok
    $0.068 / $0.168 (best)
    digitalocean
  • Azure95.85%
    Degraded24h 89.29%
    7d
    85.76%
    30d
    85.76%
    p50
    1.84s
    p99
    17.1s
    Throughput
    28 tps
    Context
    1.0M
    $/Mtok
    $0.210 / $0.560
    azure/us

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

History

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.