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
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
CoreWeavecoreweave/bf16bf16 | Healthy | 100% | 99.98% | 233ms | 819ms | 121 tps | 262K | $0.100 / $0.250 |
DeepInfradeepinfra/bf16bf16 | Healthy | 100% | 99.78% | 479ms | 3.86s | 92 tps | 262K | $0.080 / $0.200 |
Venicevenice/fp4fp4 | No data | — | 99.93% | 515ms | 826ms | 208 tps | 1.0M | $0.100 / $0.250 |
- CoreWeave100%Healthy24h 99.98%
- p50
- 233ms
- p99
- 819ms
- Throughput
- 121 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.250
coreweave/bf16bf16 - DeepInfra100%Healthy24h 99.78%
- p50
- 479ms
- p99
- 3.86s
- Throughput
- 92 tps
- Context
- 262K
- $/Mtok
- $0.080 / $0.200
deepinfra/bf16bf16 - Venice—No data24h 99.93%
- p50
- 515ms
- p99
- 826ms
- Throughput
- 208 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.250
venice/fp4fp4
Measured 4m 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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.