For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see Privacy Policy(opens in new tab). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the NVIDIA API Trial Terms of Service(opens in new tab)
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.
Modalities
In / Out Price
$0.085 / $0.40per 1M
Context
1M
Released
Mar 11, 2026
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.
Nemotron 3 Super costs $0.085/M input tokens and $0.40/M output tokens.
Nemotron 3 Super has a 1,000,000 token context window. It supports up to 16,384 completion tokens.
Yes. Nemotron 3 Super accepts tools and tool_choice for function calling. It supports response_format for JSON output, without JSON-schema enforcement.
Nemotron 3 Super is served by 3 providers on OpenRouter: DeepInfra, DigitalOcean and Nebius Token Factory. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
Nemotron 3 Super was released on March 11, 2026.