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% | 260ms | 876ms | 122 tps | 262K | $0.100 / $0.250 |
DeepInfradeepinfra/bf16bf16 | Healthy | 100% | 99.78% | 368ms | 4.12s | 79 tps | 262K | $0.080 / $0.200 |
Venicevenice/fp4fp4 | Healthy | 100% | 99.93% | 521ms | 1.06s | 227 tps | 1.0M | $0.100 / $0.250 |
- CoreWeave100%Healthy24h 99.98%
- p50
- 260ms
- p99
- 876ms
- Throughput
- 122 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.250
coreweave/bf16bf16 - DeepInfra100%Healthy24h 99.78%
- p50
- 368ms
- p99
- 4.12s
- Throughput
- 79 tps
- Context
- 262K
- $/Mtok
- $0.080 / $0.200
deepinfra/bf16bf16 - Venice100%Healthy24h 99.93%
- p50
- 521ms
- p99
- 1.06s
- Throughput
- 227 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
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.