modelstatus.dev

R1 0528

deepseek/deepseek-r1-0528

Compare with DeepSeek V3, R1, R1 Distill Llama 70B

CompareR1 0528
  • Healthy24h 99.98%
    7d
    99.62%
    30d
    99.62%
    p50
    630ms
    p99
    2.42s
    Throughput
    28 tps
    Context
    164K
    $/Mtok
    $0.500 / $2.15
    deepinfra/fp4fp4
  • Healthy24h 99.37%
    7d
    99.47%
    30d
    99.47%
    p50
    1.43s
    p99
    12.4s
    Throughput
    18 tps
    Context
    164K
    $/Mtok
    $0.500 / $2.18
    siliconflow/fp8fp8
  • No data24h 100%
    7d
    99.91%
    30d
    99.91%
    p50
    1.50s
    p99
    2.93s
    Throughput
    25 tps
    Context
    164K
    $/Mtok
    $0.700 / $2.50
    novita/fp8fp8
  • No data24h 99.87%
    7d
    99.83%
    30d
    99.83%
    p50
    3.50s
    p99
    12.0s
    Throughput
    41 tps
    Context
    128K
    $/Mtok
    $0.571 / $2.29
    streamlake

Measured 52s ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

2 endpoints reporting no data are omitted from the charts.

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.