NVIDIA Nemotron 3 Super 120B (Public Preview) API
About
Build advanced reasoning agents with NVIDIA Nemotron 3 Super 120B (Public Preview), 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 $0.65/1M output tokens, native tool calling support, open weights architecture. Access NVIDIA Nemotron 3 Super 120B (Public Preview) via the DigitalOcean API with up to 33K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
Yes
Tool Use
Yes
WeightsOpen
Limits
Context Window
1.0M
Tokens
Input Limit
1.0M
Tokens
Max Output
33K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.30
Output
$0.65
Caching (per 1M tokens)
Read
$0.06
Frequently Asked Questions
NVIDIA Nemotron 3 Super 120B (Public Preview) by DigitalOcean costs $0.30 per 1M input tokens and $0.65 per 1M output tokens. Cached reads cost $0.06 per 1M tokens.
Model Details
ID
nvidia-nemotron-3-super-120b
Provider
DigitalOceanFamily
nemotron
Release Date
Mar 11, 2026
Knowledge Cutoff
Feb 1, 2026
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
DIGITALOCEAN_ACCESS_TOKEN
API Base URL
https://inference.do-ai.run/v1