LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Nemotron 3 Super 120B A12B

nvidia·nvidia/nemotron-3-super-120b-a12b·GA·Open weights·nemotron series
Nemotron middle tier for collaborative agents and high-volume reasoning workloads

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·NanoGPTGateway
$0.05 / $0.25
Blended $0.10 · 158.7× spread
2 more $0 channels
Context
131,072
Output limit
131,072
Knowledge cutoff
2025-06
Released / updated
2026-03-11 / 2026-03-11
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text

Nemotron 3 Super 120B A12B by nvidia is offered by 21 providers on this page. Public prices are shown for 19 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is NanoGPT at $0.05 / $0.25 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 159× across the providers that host it. It also has 2 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 125 tokens per second, with 0.7s to the first token.

The context window is 131,072 tokens at the reference host, but hosts report different limits, from 65,536 to 1,000,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-06.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier Reasoning

Intelligence—
Value—
Output speed125 tok/s
TTFT0.7 s

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

Available at 21 providers19 with public prices · 2 free

  • ProviderInput / Output
  • AIHubMixGateway
    nemotron-3-super-120b-a12b-free
    Free
    Context 262,144 ⚠Output limit 262,144
  • OpenCodeGateway
    nemotron-3-super-free
    Free
    Cache read $0Context 204,800 ⚠Output limit 128,000deprecated
  • NanoGPTGateway
    $0.05 / $0.25
    Cache read $0.025Context 262,144 ⚠Output limit 16,384
  • NanoGPTGateway
    nvidia/nemotron-3-super-120b-a12b:thinking
    $0.05 / $0.25
    Cache read $0.025Context 262,144 ⚠Output limit 16,384
  • Kilo GatewayGateway
    $0.06 / $0.32
    Context 262,144 ⚠Output limit 16,384
  • OpenRouterGateway
    $0.075 / $0.40
    Context 262,144 ⚠Output limit 16,384
  • Eden AIGateway
    $0.075 / $0.40
    Context 262,144 ⚠Output limit 262,144
  • Ollama CloudCloud
    nemotron-3-super
    $0.015 / $0.60
    Cache read $0.015Context 262,144 ⚠Output limit 65,536
  • KenariGateway
    $0.097 / $0.48
    Cache read $0.0097Context 262,144 ⚠Output limit 262,144
  • RequestyGateway
    nvidia-nemotron-3-super-120b-a12b
    $0.10 / $0.50
    Context 262,144 ⚠Output limit 262,144
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
AIHubMix
nemotron-3-super-120b-a12b-free
GatewayFree——262,144 ⚠262,144
OpenCode
nemotron-3-super-free
GatewayFree$0—204,800 ⚠128,000deprecated
NanoGPTGateway$0.05$0.25$0.025—262,144 ⚠16,384
NanoGPT
nvidia/nemotron-3-super-120b-a12b:thinking
Gateway$0.05$0.25$0.025—262,144 ⚠16,384
Kilo GatewayGateway$0.06$0.32——262,144 ⚠16,384
OpenRouterGateway$0.075$0.40——262,144 ⚠16,384
Eden AIGateway$0.075$0.40——262,144 ⚠262,144
Ollama Cloud
nemotron-3-super
Cloud$0.015$0.60$0.015—262,144 ⚠65,536
KenariGateway$0.097$0.48$0.0097—262,144 ⚠262,144
Requesty
nvidia-nemotron-3-super-120b-a12b
Gateway$0.10$0.50——262,144 ⚠262,144

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.

Reasoning control

budget_tokensToggle (on / off)effort = noneeffort = loweffort = mediumeffort = higheffort = maxeffort = xhigh

Interleaved thinking (reasoning between tool calls) is declared by 3 of 21 providers.

4 / 21 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1NanoGPT$19.50
2NanoGPT$19.50
3Kilo Gateway$28.00
4Kenari$32.93
5Ollama Cloud$33.00
6OpenRouter$35.00

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

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.80$02026-08-052026-10-15
2026-10-15Input list —Output list —Min blended $0.10

Related models

Nemotron 3.5 Super VL 120B A12Bsame series$0 / $0Nemotron 3.5 Super 120B A12Bsame series—Nemotron 3.5 Lightning 30B A3Bsame series$0 / $0Nemotron 3 Nano Omni 30B A3B Reasoningsame lab$0 / $0Nemotron 3 Ultra 550B A55Bsame lab$0 / $0
Data partly from models.dev (MIT)