Pass IndexThe State of AISign in

Nemotron 3 Super

NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems.

text → text · made by NVIDIA

$0.08→$0.45per Mtok in / out
Nous Research · 8 sellers

Sold by 17 ways

SellerLaneRate
Thinking Machines Lab apitraining$0.57per Mtok in$1.44per Mtok out$0.11per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25
Thinking Machines Lab apitraining-256k$0.76per Mtok in$1.92per Mtok out$0.15per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25
Nous Research aggregatornot on the seller's list todayresold$0.068per Mtok in$0.32per Mtok outinference-api.nousresearch.com · read 2026-08-25
Nous Research aggregatorstandard$0.08per Mtok in$0.45per Mtok outinference-api.nousresearch.com · read 2026-09-12
OpenRouter 4 ways$0.3per Mtok in$2.4per Mtok out$0.15per Mtok cached
OpenRouter aggregatordekallm/fp8$0.08per Mtok in$0.45per Mtok outopenrouter.ai · read 2026-09-12
OpenRouter aggregatordeepinfra/bf16$0.085per Mtok in$0.4per Mtok outopenrouter.ai · read 2026-09-15
OpenRouter aggregatorstandard$0.3per Mtok in$2.4per Mtok out$0.15per Mtok cachedopenrouter.ai · read 2026-10-21
OpenRouter aggregatorcrusoe/fp8$0.3per Mtok in$2.4per Mtok out$0.15per Mtok cachedopenrouter.ai · read 2026-10-16
OpenRouter aggregatornot on the seller's list todaydigitalocean$0.3per Mtok in$0.65per Mtok out$0.06per Mtok cachedopenrouter.ai · read 2026-08-25
DeepInfra aggregatorstandard$0.085per Mtok in$0.4per Mtok outapi.deepinfra.com · read 2026-09-02
Inference.net aggregatorstandard$0.1per Mtok in$0.48per Mtok out$2.5per Mtok cachedapi.inference.net · read 2026-10-31
Featherless AI aggregatorstandard$0.12per Mtok in$1.15per Mtok outapi.featherless.ai · read 2026-09-20
Vercel AI Gateway aggregatorstandard$0.15per Mtok in$0.65per Mtok outai-gateway.vercel.sh · read 2026-08-25
Nebius Token Factory aggregatorstandard$0.3per Mtok in$0.9per Mtok outtokenfactory.nebius.com · read 2026-08-25
Requesty 0 ways$0.3per Mtok in$0.9per Mtok out$0.3per Mtok cached
Requesty aggregatornot on the seller's list todaynebius$0.3per Mtok in$0.9per Mtok out$0.3per Mtok cachedrouter.requesty.ai · read 2026-08-28
Cloudflare 0 ways$0.5per Mtok in$1.5per Mtok out
Cloudflare aggregatornot on the seller's list todaystandard$0.5per Mtok in$1.5per Mtok outdevelopers.cloudflare.com · read 2026-08-25
Cloudflare aggregatornot on the seller's list todaysandbox$0.5per Mtok in$1.5per Mtok outdevelopers.cloudflare.com · read 2026-08-25

Measured 6 standings

PlaceBoardMetricScore
107thof 131Artificial Analysis · Agentic IndexIndex1.7
113thof 163Artificial Analysis · Coding IndexIndex37.7
126thof 173Weirdml — Epoch AIAccuracy38.01
129thof 132Ale bench — Epoch AIPerformance213.9
152ndof 260Critpt — Epoch AIAccuracy3.143
205thof 235Scicode — Epoch AIScore35.995

About

Nemotron 3 Super — a text model from NVIDIA, sold by 8 companies from $0.08 in and $0.45 out per million tokens, placed 152nd of 260 on Critpt — Epoch AI.

It takes text and returns text, with a context window of 262,144 tokens. It was published in March 2026, trained on material up to February 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under chat. Eight companies sell it. The cheapest is $0.08 in and $0.45 out per million tokens at Nous Research. Beside the standard rate there are regional and separately routed lanes. It has been measured on 6 boards, and stands best at 152nd of 260 on Critpt — Epoch AI.

Every current figure

Maker
NVIDIA
Register
model
Takes
text
Returns
text
Context
262,144 tokens
Published
March 2026
Knowledge to
February 2026
Parameters
124 billion
Licence
not read
Sellers
8
Maker's own price
not read
Price
$0.08 in and $0.45 out per million tokens — Nous Research
Boards
6
Best place
152nd of 260 — Critpt — Epoch AI

Known as 6 names

NVIDIA-Nemotron-3-Super@cf/nvidia/nemotron-3-120b-a12bnvidia/NVIDIA-Nemotron-3-Super-120B-A12Bnvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16nebius/nvidia/nemotron-3-super-120b-a12bnvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144