Nemotron 3.5 Lightning
nvidia/nemotron-3.5-lightning
Compare with Nemotron 3 Ultra, Nemotron 3 Nano 30B A3B, Nemotron 3 Super
Showing only the deepinfra/bf16 provider · show all 3
CompareNemotron 3.5 Lightning
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.96% | 99.67% | 99.67% | 362ms | 2.51s | 155 tps | 262K | $0.080 / $0.200 |
- DeepInfra100%Healthy24h 99.96%
- 7d
- 99.67%
- 30d
- 99.67%
- p50
- 362ms
- p99
- 2.51s
- Throughput
- 155 tps
- Context
- 262K
- $/Mtok
- $0.080 / $0.200
deepinfra/bf16bf16
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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.