Models.dev

An open-source database of AI models

Nemotron 3 Super 120B A12B

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

nvidia/nemotron-3-super-120b-a12b
Lab
NVIDIA
Family
nemotron
Providers
22
Context
262,144
Output limit
262,144
Knowledge
2025-06
Release
2026-03-11
Updated
2026-03-11
Weights
Open
Input
Output types
Capabilities
tools, reasoning, temperature

Providers

22
Providers
AIHubMixNVIDIAnemotron-3-super-120b-a12b-free262,144262,144$0.00 / $0.00YesYes-Yes
Amazon BedrockNVIDIAnvidia.nemotron-super-3-120b262,144131,072$0.15 / $0.65YesYesYesYes
BoundlessNVIDIAnemotron3-super262,144262,144$0.12 / $0.52YesYes-Yes
Cloudflare Workers AINVIDIA@cf/nvidia/nemotron-3-120b-a12b256,000256,000$0.50 / $1.50YesYesYesYes
CrusoeNVIDIAnvidia/NVIDIA-Nemotron-3-Super-120B-A12B262,144262,144$0.30 / $2.40YesYes-Yes
Eden AINVIDIAarkanecloud/nvidia/nemotron-3-super-120b-a12b256,000256,000$0.40 / $0.80YesYesNoYes
Eden AINVIDIAdeepinfra/nemotron-3-super-120b-a12b262,144262,144$0.075 / $0.40YesYesYesYes
Eden AINVIDIAnebius/nvidia/nemotron-3-super-120b-a12b262,144262,144$0.30 / $0.90YesYesNoYes
KenariNVIDIAnemotron-3-super-120b-a12b262,144262,144$0.0971 / $0.48YesYes-Yes
Kilo GatewayNVIDIAnvidia/nemotron-3-super-120b-a12b262,14416,384$0.06 / $0.32YesYesYesYes
NanoGPTNVIDIAnvidia/nemotron-3-super-120b-a12b262,14416,384$0.05 / $0.25YesNoNoYes
NanoGPTNVIDIAnvidia/nemotron-3-super-120b-a12b:thinking262,14416,384$0.05 / $0.25YesNoNoYes
Nebius Token FactoryNVIDIAnvidia/nemotron-3-super-120b-a12b262,14432,768$0.30 / $0.90YesYesYesYes
Ollama CloudNVIDIAnemotron-3-super262,14465,536$0.015 / $0.60YesYesNoYes
OpenCodeNVIDIAnemotron-3-super-free204,800128,000$0.00 / $0.00YesYes-Yes
OpenRouterNVIDIAnvidia/nemotron-3-super-120b-a12b262,14416,384$0.075 / $0.40YesYesYesYes
Perplexity AgentNVIDIAnvidia/nemotron-3-super-120b-a12b1,000,00032,000$0.25 / $2.50YesYes-Yes
RequestyNVIDIAnvidia-nemotron-3-super-120b-a12b262,144262,144$0.10 / $0.50YesYesYesYes
stepping stone AGNVIDIANVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B131,072131,072$2.38 / $5.95YesYes-Yes
Thinking MachinesNVIDIAnvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF1665,53665,536$0.57 / $1.44YesYes-Yes
Thinking MachinesNVIDIAnvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144262,144262,144$0.57 / $1.44YesYes-Yes
Vercel AI GatewayNVIDIAnvidia/nemotron-3-super-120b-a12b256,00032,000$0.15 / $0.65YesNo-Yes
No rows match the current search.

No rows match the current search.

Menu

Esc

Search

No matching results.

How to use

Models.dev is a comprehensive open-source database of AI model specifications, pricing, and features.

The homepage starts with provider-agnostic model metadata. Model pages list the providers serving that model; provider pages list every model available from that provider; lab pages group canonical models by author.

API

You can access provider data, provider-agnostic model metadata, or the combined catalog through JSON endpoints. Specialized model types are omitted by default; the site includes all model types.

Logos

Provider logos are available at /logos/{provider}.svg where {provider} is the provider ID. Lab logos are available at /logos/labs/{lab}.svg.

SDK

Use the SDK to query the API from your app. It's type-safe and exports the latest snapshot for offline use.

Contribute

The data is stored in GitHub as TOML files organized by provider and canonical model.