Models /Nemotron 3 Super /Where to run

Provider guide

Where to run Nemotron 3 Super

5 live offers tracked.

CHEAPEST

$0.085 / $0.40

per 1M tokens in / out

FASTEST MEASURED

Nebius AI Studio

134 tok/s

measured throughput · $0.30 input / $0.90 output per million tokens

ProviderIn / 1MOut / 1MThroughputContextQuantSynced

OpenRouterCHEAPEST$0.085 in/1M$0.40 out/1M—1M—14m ago DeepInfra$0.085 in/1M$0.40 out/1M—262Kbfloat166h ago DeepInfrazero-retention$0.085 in/1M$0.40 out/1M87 tok/s262Kbf163d ago DigitalOcean Gradientzero-retention$0.21 in/1M$0.46 out/1M9 tok/s1M—6h ago Nebius AI Studiozero-retention$0.30 in/1M$0.90 out/1M134 tok/s262Kfp413m ago

Full specs, hardware verdicts and benchmarks on theNemotron 3 Super model page →