Every model.One place.

NVIDIA’s open-weight 120B model (12B active) for reasoning, coding, tool use, document and GUI understanding, and video understanding. Text, images and video in; text out. A 262,144-token shared context window with responses limited to 16,384 tokens. OpenMDW 1.1 license.

Model ID

nvidia/nemotron-3.5-super-vl

Discovery tier

Open weights

Context window

262,144 tokens

Nemotron 3.5 Content Safety is a content moderation classifier that labels user messages and assistant responses as safe or unsafe. It supports a 131,072-token context window and optional reasoning.

Model ID

nvidia/nemotron-3.5-content-safety

Discovery tier

Open weights

Context window

131,072 tokens

NVIDIA's open-weight 30B mixture-of-experts model with 3B active parameters for fast agentic workflows, coding, and tool use. Running inside a TEE (Trusted Execution Environment), with provider attestation support.

Model ID

TEE/nemotron-3.5-lightning

Discovery tier

Open weights

Context window

262,144 tokens

Nvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. Thinking is disabled on this variant.

Model ID

nvidia/nemotron-3.5-lightning

Discovery tier

Open weights

Context window

1,000,000 tokens

Nvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. This variant enables its reasoning trace.

Model ID

nvidia/nemotron-3.5-lightning:thinking

Discovery tier

Open weights

Context window

1,000,000 tokens

Nvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context.

Model ID

nvidia/nemotron-3-ultra-550b-a55b

Discovery tier

Open weights

Context window

1,000,000 tokens

Nvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context. Thinking enabled.

Model ID

nvidia/nemotron-3-ultra-550b-a55b:thinking

Discovery tier

Open weights

Context window

1,000,000 tokens

Nvidia's latest Nemotron 3 Nano model with 30B total parameters (3B active) using hybrid Mamba-Transformer MoE architecture. Features excellent throughput and strong reasoning capabilities.

Model ID

nvidia/nemotron-3-nano-30b-a3b

Discovery tier

Open weights

Context window

262,144 tokens

Nvidia's Nemotron 3 Super 120B A12B model from the March 2026 Nemotron 3 release. It uses a hybrid Mamba-Transformer MoE architecture and targets agentic and coding workloads with a 262K context window here.

Model ID

nvidia/nemotron-3-super-120b-a12b

Discovery tier

Open weights

Context window

262,144 tokens

Nvidia Nemotron 3 Super 120B with reasoning content enabled. Returns separate thinking content when requested.

Model ID

nvidia/nemotron-3-super-120b-a12b:thinking

Discovery tier

Open weights

Context window

262,144 tokens

OpenReasoning-Nemotron-32B is a reasoning model derived from Qwen2.5-32B-Instruct, post-trained for math, science, and code solution generation. Evaluated with up to 64K output tokens. Available in multiple sizes: 1.5B, 7B, 14B, and 32B.

Model ID

pamanseau/OpenReasoning-Nemotron-32B

Discovery tier

Open weights

Context window

32,768 tokens

Llama-3.3-Nemotron-Super-49B-v1 is a model which offers a great tradeoff between model accuracy and efficiency. Efficiency (throughput) directly translates to savings. Using a novel Neural Architecture Search (NAS) approach, we greatly reduce the model's memory footprint, enabling larger workloads, as well as fitting the model on a single GPU at high workloads (H200). This NAS approach enables the selection of a desired point in the accuracy-efficiency tradeoff. For more information on the NAS approach, please refer to this paper.

Model ID

nvidia/Llama-3.3-Nemotron-Super-49B-v1

Discovery tier

Open weights

Context window

128,000 tokens

Nvidia's latest Llama fine-tune optimized for instruction following. Early results hints that it might outperform models such as GPT-4o and Claude 3.5 Sonnet.

Model ID

nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

Discovery tier

Open weights

Context window

16,384 tokens