Nemotron 3 Super 120B A12B API
About
Build advanced reasoning agents with 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 $0.30/1M input and $2.40/1M output tokens, native tool calling support, open weights architecture. Access Nemotron 3 Super 120B A12B via the Crusoe API with up to 262K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
No
Tool Use
Yes
WeightsOpen
Limits
Context Window
262K
Tokens
Input Limit
262K
Tokens
Max Output
262K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.30
Output
$2.40
Caching (per 1M tokens)
Read
$0.15
Frequently Asked Questions
Nemotron 3 Super 120B A12B by Crusoe costs $0.30 per 1M input tokens and $2.40 per 1M output tokens. Cached reads cost $0.15 per 1M tokens.
Model Details
ID
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
Provider
CrusoeFamily
nemotron
Release Date
Mar 11, 2026
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
CRUSOE_API_KEY
API Base URL
https://api.inference.crusoecloud.com/v1