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.
Modalities
In / out price
$0.173 / $0.75per 1M
Context
256K
Max output
32K
Updated
Nov 5, 2026
Providers
2 routesCompare providers by price, privacy, and speed.
Amazon Bedrock | Private | $0.173 | $0.75 | — | 256K | 32K | — | — |
Surplus Intelligence | Anonymous | $0.42 | $3.35 | $0.21 | 256K | 32K | — | — |
Privacy
2 / 4Private routing
Private tier
- Anonymous
- Private
- TEE
- E2EE
Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more
Features
3Streaming
Tool calling
Reasoning
Uptime
FAQ
Common questions about NVIDIA Nemotron 3 Super 120B A12B.