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% | 272ms | 914ms | 121 tps | 262K | $0.050 / $0.200 |
DeepInfradeepinfra/fp4fp4 | Healthy | 100% | 97.91% | 303ms | 10.9s | 113 tps | 262K | $0.050 / $0.200 |
Novitanovita/fp4fp4 | Healthy | 100% | 99.89% | 374ms | 4.44s | 143 tps | 262K | $0.050 / $0.200 |
- Crusoe100%Healthy24h 99.92%
- p50
- 272ms
- p99
- 914ms
- Throughput
- 121 tps
- Context
- 262K
- $/Mtok
- $0.050 / $0.200
crusoe/fp8fp8 - DeepInfra100%Healthy24h 97.91%
- p50
- 303ms
- p99
- 10.9s
- Throughput
- 113 tps
- Context
- 262K
- $/Mtok
- $0.050 / $0.200
deepinfra/fp4fp4 - Novita100%Healthy24h 99.89%
- p50
- 374ms
- p99
- 4.44s
- Throughput
- 143 tps
- Context
- 262K
- $/Mtok
- $0.050 / $0.200
novita/fp4fp4
Measured 3m 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.