Nemotron 3 Super 120B A12B (Reasoning) API Pricing

NVIDIA · released 2026-03-11

Pricing

$0.30
input / 1M tokens
0.030¢ / 1K
$0.90
output / 1M tokens
0.090¢ / 1K
$0.45
blended / 1M tokens
0.045¢ / 1K

What it actually costs

WorkloadTokensCost
Short chat reply500 in / 300 out0.042¢
RAG query4,000 in / 500 out0.165¢
Long document summary50,000 in / 1,000 out$0.0159
Code review of a 2k-line file30,000 in / 2,000 out$0.0108
1,000 chat replies/day for 30 days30,000 × (500 in / 300 out)$12.60

Cost = (input tokens ÷ 1,000,000 × $0.30) + (output tokens ÷ 1,000,000 × $0.90).

Benchmarks

12.8
Intelligence
#206 of 533
37.7
Coding
#98 of 197
Math
164
Tokens/sec
1.04s
Time to first token

Similar intelligence, lower price

ModelIntelligenceBlended $/1M
Qwen3.5 4B (Reasoning)13.1$0.06
Nemotron 3.5 Lightning12.9$0.095
gpt-oss-20b (low)10.0$0.103
Granite 4.2 8B11.1$0.107
GPT-5 nano (high)13.0$0.138

Leaderboard neighbours

ModelIntelligenceBlended $/1M
GPT-5 nano (high)13.0$0.138
Nemotron 3.5 Lightning12.9$0.095
GLM-4.5 (Reasoning)12.8
Nemotron 3 Super 120B A12B (Reasoning)12.8$0.45
GPT-4.112.7$3.50
Kimi K212.7$1.002
Qwen3 235B A22B 2507 (Reasoning)12.7$0.747

More from NVIDIA

ModelIntelligenceBlended $/1M
Nemotron 3 Ultra 550B A55B (Reasoning)22.9$1.05
Nemotron 3.5 Lightning12.9$0.095
Nemotron Cascade 2 30B A3B11.7
Nemotron 3 Nano Omni 30B A3B Reasoning10.3$0.42
Llama Nemotron Super 49B v1.5 (Reasoning)9.0$0.40
Llama 3.3 Nemotron Super 49B v1 (Reasoning)8.9
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)8.9$0.088
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)7.5

Count tokens & estimate cost for Nemotron 3 Super 120B A12B (Reasoning) See Nemotron 3 Super 120B A12B (Reasoning) on the leaderboard

Source: Artificial Analysis · last synced 2026-09-22

FAQ

Who develops Nemotron 3 Super 120B A12B (Reasoning)?

Nemotron 3 Super 120B A12B (Reasoning) is developed by NVIDIA, released 2026-03-11.

How much does Nemotron 3 Super 120B A12B (Reasoning) cost per million tokens?

Nemotron 3 Super 120B A12B (Reasoning) costs $0.30 per 1M input tokens and $0.90 per 1M output tokens ($0.45 blended), per Artificial Analysis's official pricing data.

How does Nemotron 3 Super 120B A12B (Reasoning) rank on benchmarks?

Nemotron 3 Super 120B A12B (Reasoning) scores 12.8 on the Artificial Analysis Intelligence Index, ranking #206 of 533 models we track.

Is there a cheaper model with similar intelligence to Nemotron 3 Super 120B A12B (Reasoning)?

Yes — Qwen3.5 4B (Reasoning) scores similar intelligence (13.1) at $0.06/1M blended, versus $0.45/1M for Nemotron 3 Super 120B A12B (Reasoning).

Where does this data come from?

Pricing and benchmark data for Nemotron 3 Super 120B A12B (Reasoning) comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.