Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3b
Compare with Nemotron 3 Nano 30B A3B (free), Nemotron 3 Nano Omni (free), Nemotron 3 Ultra
CompareNemotron 3 Nano 30B A3B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Crusoecrusoe/fp8fp8 | Healthy | 100% | 99.92% | 251ms | 1.13s | 114 tps | 262K | $0.050 / $0.200 |
Novitanovita/fp4fp4 | Healthy | 100% | 99.90% | 378ms | 2.52s | 112 tps | 262K | $0.050 / $0.200 |
DeepInfradeepinfra/fp4fp4 | Healthy | 99.34% | 97.88% | 278ms | 8.08s | 101 tps | 262K | $0.050 / $0.200 |
- Crusoe100%Healthy24h 99.92%
- p50
- 251ms
- p99
- 1.13s
- Throughput
- 114 tps
- Context
- 262K
- $/Mtok
- $0.050 / $0.200
crusoe/fp8fp8 - Novita100%Healthy24h 99.90%
- p50
- 378ms
- p99
- 2.52s
- Throughput
- 112 tps
- Context
- 262K
- $/Mtok
- $0.050 / $0.200
novita/fp4fp4 - DeepInfra99.34%Healthy24h 97.88%
- p50
- 278ms
- p99
- 8.08s
- Throughput
- 101 tps
- Context
- 262K
- $/Mtok
- $0.050 / $0.200
deepinfra/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.
Throughput
Median tokens per second.