Models Pricing Docs Blog Contact

Sign In Sign Up Free

High-speed, scalable, sub-100ms serverless inference API cloud for production AI models. Up to 10x lower cost than closed APIs.

All Edge Endpoints Operational

Model Types

Image To Video Generation
Text Generation
Text To Image
Speech Recognition (ASR)
Speech Synthesis (TTS)
Embeddings

Popular Providers

Meta AI
DeepSeek AI
Black Forest Labs
Mistral AI
Qwen / Alibaba Cloud
Hexgrad
OpenAI Whisper

Resources

Pricing & Token Rates
API Documentation
Developer Blog
Contact & Support

Subscribe to API Drops & Model Releases

Get notified about new open-source model benchmarks, speed updates, and pricing drops.

© 2026 WhollyAPI. All rights reserved.

Privacy Policy Terms of Service Refund Policy Cookie Policy

NVIDIA-Nemotron-3-Super-120B-A12B | WhollyAPI

Home
Models
NVIDIA-Nemotron-3-Super-120B-A12B

ServerlessText Generation

NVIDIA-Nemotron-3-Super-120B-A12B

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B

NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following.

PublicSupports Priority TierSupports Flex Tierbfloat16JSONFunction

NVIDIA-Nemotron-3-Super-120B-A12B

NVIDIA-Nemotron-3-Super-120B-A12B

NVIDIA-Nemotron-3-Super-120B-A12B

OpenAI Compatible

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B

Start a conversation with NVIDIA-Nemotron-3-Super-120B-A12B

Test OpenAI chat completion requests live directly with WhollyAPI serverless API.

Suggested Prompts

Press Shift + Enter for line breaks

Similar models

claude-fable-5

$10 / 1M tokens

claude-haiku-4-5

$1 / 1M tokens

claude-opus-4-7

$5 / 1M tokens