NVIDIA: Nemotron 3 Super (free)
Analysis Summary
NVIDIA: Nemotron 3 Super (free) sits in the Emerging tier on our leaderboard, ranked #508 of 525 published models on overall intelligence. At $0.000 input and $0.000 output per 1M tokens, it is among the most expensive on the market. It offers a generous context window for extended reasoning and code review and supports tool use and function calling.
Editorial notes
The free tier of NVIDIA's Nemotron 3 Super offers the same large 262K context window and tool use capabilities as its paid sibling at no cost — a useful option for testing and low-volume workloads, though benchmark data is not independently available for this variant.
Assessed April 23, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer..
Capabilities
How does NVIDIA: Nemotron 3 Super (free) stack up?
Compare side-by-side with other emerging models.
Model Information
| OpenRouter ID |
nvidia/nemotron-3-super-120b-a12b:free
|
| Provider | nvidia |
| Release Date | March 11, 2026 |
| Context Length | 262,144 tokens |
| Max Completion | 262,144 tokens |
| Status | Active |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
