Nemotron 3 Ultra vs Nemotron 3 Ultra (batch)
One line per model: the best value available from any of its providers at each point, which is what a caller routing to the healthy endpoint would see.
CompareNemotron 3 UltraNemotron 3 Ultra (batch)
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| Nemotron 3 Ultra | 2/4 | 100% BaseTen | 528ms BaseTen | 5.28s BaseTen | 75 tps Together | 512K | $0.500 / $2.20 DeepInfra |
| Nemotron 3 Ultra (batch) | 0/1 | — | — | — | — | 512K | $0.600 / $3.60 Together |
Measured 1m ago. Each figure is the best available across that model's providers.
History
Availability
Best uptime available from any provider. Axis starts at 90%; it expands to 0 when a model falls below.
Time to first token
Fastest p50 available from any provider. Logarithmic axis.
Throughput
Best median tokens per second available.