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% | 244ms | 1.50s | 174 tps | 262K | $0.100 / $0.250 |
DeepInfradeepinfra/bf16bf16 | Healthy | 100% | 99.82% | 381ms | 2.77s | 132 tps | 262K | $0.080 / $0.200 |
Venicevenice/fp4fp4 | Healthy | 100% | 99.94% | 508ms | 1.64s | 95 tps | 1.0M | $0.100 / $0.250 |
- CoreWeave100%Healthy24h 99.98%
- p50
- 244ms
- p99
- 1.50s
- Throughput
- 174 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.250
coreweave/bf16bf16 - DeepInfra100%Healthy24h 99.82%
- p50
- 381ms
- p99
- 2.77s
- Throughput
- 132 tps
- Context
- 262K
- $/Mtok
- $0.080 / $0.200
deepinfra/bf16bf16 - Venice100%Healthy24h 99.94%
- p50
- 508ms
- p99
- 1.64s
- Throughput
- 95 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.250
venice/fp4fp4
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
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.