Model scorecard
NVIDIA nemotron-ultra-253b-v1
Composite 67.1/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B+67.1/100nvidia/nemotron-ultra-253b-v1text · 128k context
Capability
eval compositeQuality (blended eval)87
Category: reasoning
Usable context6
128k advertised window
Serving
gateway measuredThroughput34
120 output tokens/s median
Time to first token57
260ms p50
Economics
at provider costPrice efficiency70
$1.60 per 1M output tokens
Quality per dollar100
llmcloud adds $0 to these token prices.
Suggested usage
Not a default pick today. It is a reasonable explicit choice when you need this vendor specifically, or as a failover target inside auto:reasoning.
→ Full workload matrix