NVIDIA: Nemotron 3 Super
micronvidia/nemotron-3-super-120b-a12b
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
AA INDEX12.8
CONTEXT262K
MODALITYtext->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED24 min ago
Input
$0.09 /M
Output
$0.45 /M
Blended (40/60)
$0.30 /M
Cost / IQ
$0.9437 /M
Cost / IQ = Blended Price ÷ (AA Intelligence Score ÷ 40). Normalises price by model intelligence so you can compare value across tiers. Lower = better value per unit of intelligence. Not a transactional price.
24h0%
7d↑ 4.9%
Price History
30-day view, daily close
Low: $0.29/M
High: $0.30/M
Average: $0.29/M
Cost / IQ Comparison
Cost / IQ (quality-adjusted $/M)$0.9437/M
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
At or below SIT TPI
Value Ranking (by Cost / IQ)
Rank #393 of 522 micro models
← YOU ARE HERE | NVIDIA: Nemotron 3 Super
Data Sources
Source
Aggregator & direct provider data
3 sources · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/nvidia/nemotron-3-super-120b-a12b
# Response (truncated)
{ "model_id": "nvidia/nemotron-3-super-120b-a12b", "name": "NVIDIA: Nemotron 3 Super", "blended_price_per_m": 0.302, "sit_adjusted_price": 0.94375 }