NVIDIA Nemotron 3 Super 120B A12B API
About
Build advanced reasoning agents with NVIDIA Nemotron 3 Super 120B A12B, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.15/1M input and $0.65/1M output tokens, native tool calling support, open weights architecture. Access NVIDIA Nemotron 3 Super 120B A12B via the Amazon Bedrock API with up to 131K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
Yes
Tool Use
Yes
WeightsOpen
Limits
Context Window
262K
Tokens
Input Limit
262K
Tokens
Max Output
131K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.15
Output
$0.65
Frequently Asked Questions
NVIDIA Nemotron 3 Super 120B A12B by Amazon Bedrock costs $0.15 per 1M input tokens and $0.65 per 1M output tokens.
Model Details
ID
nvidia.nemotron-super-3-120b
Provider
Amazon BedrockFamily
nemotron
Release Date
Mar 11, 2026
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/amazon-bedrock
Environment Variables
AWS_ACCESS_KEY_ID
AWS_SECRET_ACCESS_KEY
AWS_REGION
AWS_BEARER_TOKEN_BEDROCK