modelstatus.dev

Nemotron 3.5 Super VL

nvidia/nemotron-3.5-super-vlInputtextimagevideoOutputtext

Compare its 5 providersIncident RSSCompare with Nemotron 3.5 Lightning, Nemotron 3.5 Content Safety, Nemotron 3 Ultra

CompareNemotron 3.5 Super VL
  • Healthy24h 99.03%
    7d
    100%
    30d
    100%
    p50
    926ms
    p99
    34.2s
    Throughput
    117 tps
    Context
    262K
    $/Mtok
    $0.150 / $0.500
    together
  • Crusoe80.00%
    Down24h 95.10%
    7d
    96.84%
    30d
    96.84%
    p50
    454ms
    p99
    25.9s
    Throughput
    90 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.400
    crusoe/bf16bf16
  • Degraded24h 92.80%
    7d
    72.63%
    30d
    72.63%
    p50
    573ms
    p99
    3.64s
    Throughput
    270 tps
    Context
    1.0M
    $/Mtok
    $0.150 / $0.750
    coreweave/nvfp4nvfp4
  • No data24h 99.73%
    7d
    100%
    30d
    100%
    p50
    614ms
    p99
    2.08s
    Throughput
    380 tps
    Context
    262K
    $/Mtok
    $0.200 / $1.00
    deepinfra/fp4fp4
  • No data24h 100%
    7d
    100%
    30d
    100%
    p50
    1.12s
    p99
    10.4s
    Throughput
    203 tps
    Context
    262K
    $/Mtok
    $0.250 / $1.25
    venice/fp4fp4

Measured 1m 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.

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 · 5 endpoints · 1 day with data, 2 endpoint-days below 90%.