modelstatus.dev

DeepSeek V3.1 Terminus

deepseek/deepseek-v3.1-terminus

Compare with DeepSeek V3.1, DeepSeek V3, DeepSeek V3.2

CompareDeepSeek V3.1 Terminus
  • AtlasCloud100%
    Healthy24h 99.40%
    p50
    1.74s
    p99
    7.55s
    Throughput
    40 tps
    Context
    131K
    $/Mtok
    $0.300 / $0.950
    atlas-cloud/fp8fp8
  • Novita100%
    Healthy24h 99.97%
    p50
    1.97s
    p99
    8.48s
    Throughput
    19 tps
    Context
    131K
    $/Mtok
    $0.270 / $1.00
    novita/fp8fp8
  • StreamLake100%
    Healthy24h 99.92%
    p50
    1.59s
    p99
    12.1s
    Throughput
    45 tps
    Context
    128K
    $/Mtok
    $0.343 / $1.03
    streamlake
  • SiliconFlow96.30%
    Healthy24h 97.67%
    p50
    1.52s
    p99
    19.2s
    Throughput
    17 tps
    Context
    164K
    $/Mtok
    $0.270 / $1.00
    siliconflow/fp8fp8

Measured 2m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.

Throughput

Median tokens per second.