by Nvidia
An open-source, efficient hybrid Mamba-Transformer MoE model that supports a context length of one million tokens and excels at agent reasoning, programming, planning, and tool invocation.
An open-source, efficient hybrid Mamba-Transformer MoE model that supports a context length of one million tokens and excels at agent reasoning, programming, planning, and tool invocation.
nvidia-nemotron-3-super-120b-a12b has a 1,000,000 token context window.
On AIHubMix, nvidia-nemotron-3-super-120b-a12b costs $0.11 per million input tokens and $0.55 per million output tokens. Cached input reads are billed at $0.03 per million tokens.
nvidia-nemotron-3-super-120b-a12b accepts text input.
nvidia-nemotron-3-super-120b-a12b supports thinking, tool calling, function calling, structured outputs and long context. Per-protocol parameter support is listed in the capability table on this page.
nvidia-nemotron-3-super-120b-a12b is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to nvidia-nemotron-3-super-120b-a12b — no other code changes needed.
nvidia-nemotron-3-super-120b-a12b is developed by Nvidia. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
NVIDIA-Nemotron-Nano-9B-v2-free is a large language model trained from scratch by NVIDIA…
Developed by Nvidia, Nemotron-Nano-12B-V2-VL-Free is a 12-billion-parameter open…
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model built on a hybrid…
Developed by Nvidia, NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model…
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model featuring…
Developed by NVIDIA, Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal…
Use nvidia-nemotron-3-super-120b-a12b via the AIHubMix unified API — one interface for every major LLM.