nvidia

NVIDIA: Nemotron 3 Super (free)

by nvidia

OpenRouter
Tools Reasoning Long Context

About

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 Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models. The model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified. Fully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.

Specifications

Context Length 262K
Max Output Tokens 262K
Modality text->text
Input text
Output text
Supported Parameters include_reasoning, max_tokens, reasoning, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_p
Content Moderation No

Error Rate

Based on feedback reported by Free LLM Router users. Error rate reflects the percentage of requests that encountered issues such as rate limiting, unavailability, or errors. Learn more.

Loading chart...
Model 1h 6h 24h 7d 30d
NVIDIA: Nemotron 3 Super (free) 0.0% 0.0% 0.0% 0.0% 6.3%

Availability

Available 9 of 9 tracked days. Daily snapshots show whether this model was accessible as a free model on OpenRouter.

FebMar
ModelDays181920212223242526272812345678910111213141516171819
NVIDIA: Nemotron 3 Super (free)9

Similar Models

More from Nvidia

Frequently Asked Questions

Is NVIDIA: Nemotron 3 Super (free) free to use?

Yes, NVIDIA: Nemotron 3 Super (free) is completely free to use through OpenRouter. You can access it via the Free LLM Router API at no cost.

What is the context window for NVIDIA: Nemotron 3 Super (free)?

NVIDIA: Nemotron 3 Super (free) supports a context window of 262K tokens (262,144 tokens).

What is the maximum output length for NVIDIA: Nemotron 3 Super (free)?

NVIDIA: Nemotron 3 Super (free) can generate up to 262K tokens (262,144 tokens) per response.

Does NVIDIA: Nemotron 3 Super (free) support function calling (tools)?

Yes, NVIDIA: Nemotron 3 Super (free) supports function calling / tool use, enabling it to interact with external APIs and services.

Does NVIDIA: Nemotron 3 Super (free) support reasoning?

Yes, NVIDIA: Nemotron 3 Super (free) supports reasoning capabilities, allowing it to show its step-by-step thought process.