modelstatus.dev

Nemotron 3 Ultra

nvidia/nemotron-3-ultra-550b-a55b

Compare with Nemotron 3 Ultra (batch), Nemotron 3 Ultra (free), Nemotron 3 Nano 30B A3B

CompareNemotron 3 Ultra
  • Healthy24h 94.29%
    7d
    95.02%
    30d
    95.02%
    p50
    485ms
    p99
    5.26s
    Throughput
    83 tps
    Context
    203K
    $/Mtok
    $0.600 / $2.40
    baseten/fp4fp4
  • Together99.52%
    Healthy24h 98.03%
    7d
    98.52%
    30d
    98.52%
    p50
    686ms
    p99
    11.2s
    Throughput
    85 tps
    Context
    512K
    $/Mtok
    $0.600 / $3.60
    together
  • DeepInfra91.32%
    Degraded24h 88.27%
    7d
    91.22%
    30d
    91.22%
    p50
    2.50s
    p99
    18.5s
    Throughput
    36 tps
    Context
    262K
    $/Mtok
    $0.500 / $2.20
    deepinfra/fp4fp4
  • Degraded24h 73.84%
    7d
    82.33%
    30d
    82.33%
    p50
    2.43s
    p99
    99.4s
    Throughput
    21 tps
    Context
    256K
    $/Mtok
    $0.625 / $3.13
    venice/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 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.