modelbenchmark.io

Nvidia Nemotron 3 Nano 30B

NVIDIA · nemotron-3-nano-30b-a3b

Compare

Small Nemotron 3 MoE for efficient coding, math, and long-context agents

Specification

most-agreed values

Context
262K
Max output
236K
Released
2025-12-15
Knowledge cutoff
2024-09
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.05
Output
$0.20
Cache read
$0.025

Available from 9 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kenarifreefree262K262K
nvidiafreefree131K131K
deepinfra$0.05$0.20$0.025262K262K
edenai$0.05$0.20$0.025262K262K
kilo$0.05$0.20$0.03262K236K
novita$0.05$0.20262K33K
openrouter$0.05$0.20$0.03262K236K
vercel$0.05$0.20$0.025262K262K
nano-gpt$0.17$0.68$0.085262K236K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02kiloCache read$0.025
2026-09-03kiloCache read$0.03
2026-09-02openrouterCache read$0.025
2026-09-03openrouterCache read$0.03
2026-09-06openrouterCache read$0.03
2026-09-02openrouterInput$0.05
2026-09-06openrouterInput$0.05
2026-09-02openrouterOutput$0.20
2026-09-06openrouterOutput$0.20
2026-09-02vercelOutput$0.24
2026-09-15vercelOutput$0.20

Other listings of this model

same model, different key

More from NVIDIA

most-hosted first