Nemotron 3 Ultra
nvidia/nemotron-3-ultra-550b-a55b
Compare with Nemotron 3 Ultra (batch), Nemotron 3 Ultra (free), Nemotron 3 Nano 30B A3B
CompareNemotron 3 Ultra
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
BaseTenbaseten/fp4fp4 | Healthy | 100% | 98.85% | 528ms | 5.28s | 55 tps | 203K | $0.600 / $2.40 |
Togethertogether | Healthy | 98.95% | 98.58% | 673ms | 8.05s | 75 tps | 512K | $0.600 / $3.60 |
DeepInfradeepinfra/fp4fp4 | Degraded | 95.17% | 92.16% | 2.22s | 16.8s | 68 tps | 262K | $0.500 / $2.20 |
Venicevenice/fp8fp8 | Degraded | 95.12% | 87.49% | 1.22s | 9.62s | 28 tps | 256K | $0.625 / $3.13 |
- BaseTen100%Healthy24h 98.85%
- p50
- 528ms
- p99
- 5.28s
- Throughput
- 55 tps
- Context
- 203K
- $/Mtok
- $0.600 / $2.40
baseten/fp4fp4 - Together98.95%Healthy24h 98.58%
- p50
- 673ms
- p99
- 8.05s
- Throughput
- 75 tps
- Context
- 512K
- $/Mtok
- $0.600 / $3.60
together - DeepInfra95.17%Degraded24h 92.16%
- p50
- 2.22s
- p99
- 16.8s
- Throughput
- 68 tps
- Context
- 262K
- $/Mtok
- $0.500 / $2.20
deepinfra/fp4fp4 - Venice95.12%Degraded24h 87.49%
- p50
- 1.22s
- p99
- 9.62s
- Throughput
- 28 tps
- Context
- 256K
- $/Mtok
- $0.625 / $3.13
venice/fp8fp8
Measured 2m 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.