← Model list

Nemotron 3 Super 120B A12B

nvidia·nvidia/nemotron-3-super-120b-a12b-3·GA·Open weights·nemotron series

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

At a glance
Reference price$0.30 / $1.00 per 1M
Cache read $0.30 · Synthetic
Lowest paid$0.085 / $0.40
OpenRouter Gateway · 3.5× spread
2 more $0 channels
Context262,144
⚠ Providers report 8,000–1,048,576; the table below is authoritative
Output limit65,536
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2026-02
Released / updated2026-03-11 / 2026-03-11

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Reasoning

Intelligence25.7
Value157
Coding37.7
Agentic8.8
Output speed129 tok/s
TTFT2 s
Cost per task$0.2286
Value formulaIQ 25.7 ÷ min blended $0.164 = 157

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 10 providers8 with public prices · 2 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Kenari
nemotron-3-super-120b-a12b
GatewayFree262,144262,144
Requesty
nemotron-3-super-120b-a12b
GatewayFree1,048,57665,536
OpenRouter
nvidia/nemotron-3-super-120b-a12b
Gateway$0.085$0.401,000,00016,384
Eden AI
flexai/Nemotron-3-Super-120B-A12B
Gateway$0.085$0.40262,144262,144
Kilo Gateway
nvidia/nemotron-3-super-120b-a12b
Gateway$0.085$0.40262,14416,384
Pioneer
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
Gateway$0.09$0.45$0.09$0.09256,00032,000
Nebius Token Factory
nvidia/nemotron-3-super-120b-a12b
Cloud$0.30$0.90256,00032,768
Eden AI
nebius/nvidia/nemotron-3-super-120b-a12b
Gateway$0.30$0.90$0.308,000262,144
TensorX
nvidia/nemotron-3-super-120b-a12b
Gateway$0.30$0.90$0.075$0.375262,144262,144
Synthetic
hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4
Gateway$0.30$1.00$0.30262,14465,536

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1OpenRouter$37.00
2Eden AI$37.00
3Kilo Gateway$37.00
4Pioneer$40.50
5TensorX$78.00
6Nebius Token Factory$105.00

2 more channels offer $0 (Kenari, Requesty); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

effort = loweffort = mediumeffort = noneeffort = higheffort = maxbudget_tokensToggle (on / off)effort = minimaleffort = xhigh

1 / 10 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input list $0.30Output list $1.00Min blended $0.164

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-13). Each future sync adds a point, and once accumulated a line is drawn here.