modelstatus.dev

Nemotron 3.5 Lightning

nvidia/nemotron-3.5-lightning

Compare with Nemotron 3 Ultra, Nemotron 3 Nano 30B A3B, Nemotron 3 Super

CompareNemotron 3.5 Lightning

	State
CoreWeavecoreweave/bf16bf16	Healthy	100%	97.93%	99.68%	99.68%	1.40s	9.96s	107 tps	262K	$0.100 / $0.250
DeepInfradeepinfra/bf16bf16	Healthy	100%	99.97%	99.66%	99.66%	476ms	1.64s	77 tps	262K	$0.080 / $0.200
Venicevenice/fp4fp4	No data	—	—	99.99%	99.99%	—	—	—	1.0M	$0.100 / $0.250

CoreWeave100%
Healthy24h 97.93%
7d
99.68%
30d
99.68%
p50
1.40s
p99
9.96s
Throughput
107 tps
Context
262K
$/Mtok
$0.100 / $0.250
coreweave/bf16bf16
DeepInfra100%
Healthy24h 99.97%
7d
99.66%
30d
99.66%
p50
476ms
p99
1.64s
Throughput
77 tps
Context
262K
$/Mtok
$0.080 / $0.200
deepinfra/bf16bf16
Venice—
No data24h —
7d
99.99%
30d
99.99%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.100 / $0.250
venice/fp4fp4

Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

1 endpoint reporting no data is 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.