Models

nemotron-3-super-120b-a12b

openrouter · 262K ctx · 3 providers · updated 2026-09-19 02:15 UTC

Cheapest
$0.172 Official list · OpenRouter
Avg price
$0.265 /1M
providers
3
Tokens (24h)
52B
Volume (24h)
$0 est.
(3 × $0.080 + $0.450) ÷ 4 = $0.172/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.080, 3:1 $0.172, 1:1 $0.265, output only $0.450 per 1M.

The board shows this model's cheapest measured offer ($0.172/1M); the smaller figure under it is the mean of the 3 offers listed below ($0.265/1M). Add those up and divide — it matches. 24h token volume (52B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
openrouter Pricebook (LiteLLM) $0.080$0.450 Official list
openrouter-best OpenRouter $0.080$0.450 API-measured
nebius Pricebook (LiteLLM) $0.300$0.900 Official list

Volume trend

78B 30d d-29 · 63B tokensd-28 · 48B tokensd-27 · 51B tokensd-26 · 54B tokensd-25 · 62B tokensd-24 · 62B tokensd-23 · 64B tokensd-22 · 78B tokensd-21 · 71B tokensd-20 · 63B tokensd-19 · 60B tokensd-18 · 31B tokensd-17 · 0 tokensd-16 · 38B tokensd-15 · 57B tokensd-14 · 53B tokensd-13 · 54B tokensd-12 · 57B tokensd-11 · 0 tokensd-10 · 0 tokensd-9 · 58B tokensd-8 · 56B tokensd-7 · 56B tokensd-6 · 55B tokensd-5 · 54B tokensd-4 · 50B tokensd-3 · 0 tokensd-2 · 46B tokensd-1 · 47B tokensd-0 · 52B tokens

Last 30 days: 63B → 52B (-17%); range 0–78B tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/nemotron-3-super-120b-a12b.json. Free reuse requires attribution to tkx.org.

About

Nemotron 3 Super is an AI model that leverages machine learning to perform natural language processing tasks. It is served by multiple inference providers on AI model marketplaces and is listed under the organization tag "Nvidia".

AI-generated summary from public information — is this yours?

FAQ

How much does nemotron-3-super-120b-a12b cost?

Cheapest measured offer right now: $0.08/1M input, $0.45/1M output via openrouter — across 3 tracked providers, refreshed hourly.

Who serves nemotron-3-super-120b-a12b?

3 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is nemotron-3-super-120b-a12b used?

nemotron-3-super-120b-a12b routed 52B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings