NVIDIA Nemotron API

Nemotron 3 Ultra 550B A55B is NVIDIA's open-weight frontier reasoning model with 550B total and 55B active parameters, built on a hybrid Mamba-Transformer Mixture-of-Experts architecture. It supports a 1M token context window and is designed for long-running agentic workflows, complex multi-step reasoning, and high-accuracy tasks across code, math, and science. NVIDIA reports up to 5.9x higher inference throughput than comparable open MoE models. On the Artificial Analysis Intelligence Index it scores 48, leading US open-weight models and delivering the highest non-hallucination score in its comparison set (78.7 on AA-Omniscience). Choose it for production agentic pipelines, deep document analysis, or reasoning-heavy API workloads where both accuracy and throughput matter.

Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B, designed to moderate both inputs and outputs of LLMs and VLMs. It classifies prompts and responses as safe or unsafe across 23 safety categories based on the Aegis v2 taxonomy, supports 12 languages, and accepts both text and image input. An optional reasoning mode provides step-by-step chain-of-thought traces explaining each decision — useful for auditing and policy tuning. Despite its 4B size, it leads external multimodal safety benchmarks including the top harmful-F1 score on VLGuard, matching or beating 8–12B models. It also supports custom operator-defined content policies enforced at inference time. Choose it for prompt and response moderation pipelines, safety evaluation of LLM outputs, or as an inference-time guardrail in enterprise AI applications requiring explainable, policy-aware content filtering.

Nemotron 3 Nano Omni is an open multimodal model from NVIDIA that unifies text, image, video, and audio understanding in a single inference pass. Built on a 30B-parameter hybrid Mamba-Transformer Mixture-of-Experts architecture with only ~3B active parameters per token, it delivers strong reasoning at small-model inference costs. It tops six leaderboards across document intelligence (MMLongBench-Doc, OCRBenchV2), video and audio understanding (WorldSense, DailyOmni, VoiceBench), and achieves the highest throughput of any benchmarked model — open or closed — on MediaPerf's video tasks, with up to 9x higher throughput than comparable open omni models. Designed as a multimodal perception sub-agent in agentic systems, it excels at document reasoning, GUI-based computer use, speech transcription, and audio-video analysis — replacing fragmented multi-model pipelines with a single call. Supports up to 256K context with an optional reasoning mode.

Nemotron 3 Super is NVIDIA's open-weight 120B-parameter hybrid Mamba-Transformer MoE model with only 12B active parameters, designed for running complex multi-agent agentic AI systems at scale. It features a 1-million-token context window to prevent goal drift across long tasks and delivers up to 5x higher throughput than its predecessor. The model excels at reasoning, coding, and tool use.

Nemotron 3 Nano 30B A3B is a 31.6B total parameter (3.2B active) hybrid Mamba-Transformer MoE model trained from scratch by NVIDIA with a 1M token context window. It offers up to 3.3x higher throughput than comparable models and supports configurable reasoning traces for both agentic and conversational tasks.

Llama 3.3 Nemotron Super 49B v1.5 is an upgraded 49B parameter reasoning model derived from Llama 3.3 70B Instruct, optimized for single-GPU deployment on H100/H200 through Neural Architecture Search. It supports 128K context and is post-trained for agentic workflows including RAG, tool calling, and multi-turn conversations.

Nemotron Nano 9B V2 is a 9B parameter hybrid Mamba-Transformer model trained from scratch by NVIDIA with a 128K context window, achieving up to 6x higher inference throughput than similar models like Qwen3-8B. It features controllable reasoning budget allowing developers to balance accuracy and response time for edge deployment.

Nemotron Nano 12B V2 VL is a 12.6B parameter multimodal vision-language model built on a hybrid Mamba-Transformer architecture for document intelligence and video understanding. It processes multiple images, documents, and videos while achieving leading results on OCRBench v2 with up to 2.5x higher throughput using Efficient Video Sampling.

Llama 3.1 Nemotron Ultra 253B is a 253B parameter reasoning model derived from Llama 3.1 405B using Neural Architecture Search for improved efficiency, supporting 128K context and toggle ON/OFF reasoning modes. It excels at complex math, scientific reasoning, coding, RAG, and tool calling tasks while fitting on a single 8xH100 node.

Llama 3.1 Nemotron 70B Instruct is a 70B parameter LLM customized by NVIDIA using RLHF to improve response helpfulness, achieving top rankings on alignment benchmarks like Arena Hard and AlpacaEval 2 LC. It supports a 128K token context and is optimized for conversational AI and instruction-following tasks.