NVIDIA

NVIDIA is the world's leading AI computing and graphics company, founded in 1993 in the United States by Jensen Huang and others, focusing on GPUs, data-center acceleration, and AI compute platforms. Its GPUs have long held the dominant share of the dedicated graphics market, and the company has become the core compute supplier of the current AI boom, at times the most valuable company in the world. On AI, NVIDIA offers the open-source Nemotron model family and delivers training and inference infrastructure globally through DGX Cloud and the CUDA ecosystem.

AI Models

Nemotron 3.5 Super VL

NVIDIA

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video as input and returns text, and is built for long-running agents that combine visual understanding with reasoning and tool use. It uses a hybrid Mamba-Transformer architecture with multi-token prediction and supports a 1M-token context. Typical uses include document intelligence, web research, coding validation, customer service, and video understanding. Reasoning is on by default and can be turned off or given a token budget.

Context: 1M
Max output: -
Released: 2026-10-15

Input: $0.15 /M
Output: $0.5 /M

Switchyard

NVIDIA

Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most popular low and high cost models. You can pass in two choices in the models parameter as well as specify any of the routing algorithms Switchyard offers. Details in the Switchyard docs. OpenRouter then applies its normal provider routing, fallbacks and billing for the chosen model.

Context: 1M
Max output: -
Released: 2026-09-21

Nemotron 3.5 ASR Streaming Multilingual 0.6B

NVIDIA

Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice agents, and multilingual transcription pipelines.

Context: -
Max output: -
Released: 2026-08-13

Input: $3.33 /M

Nemotron 3.5 Lightning

NVIDIA

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that benefit from domain-specific customization.

Context: 262.1K
Max output: -
Released: 2026-08-11

Input: $0.07 /M
Output: $0.2 /M

Nemotron 3.5 Content Safety

NVIDIA

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting text and image input and returning text output: a safe/unsafe classification for the user prompt and the response, safety category labels, and an optional reasoning trace. It covers 12 languages with a context window of up to 128K tokens. It is suited for prompt and response moderation, content classification, safety pipelines, and enterprise AI guardrails with policy enforcement, and includes a togglable reasoning mode. It is part of the NVIDIA Nemotron family of open models for agentic AI.

Context: 131.1K
Max output: -
Released: 2026-06-04

Input: $0.2 /M
Output: $0.2 /M

Nemotron 3 Ultra

NVIDIA

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks. It is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.

Context: 262.1K
Max output: -
Released: 2026-06-04

Input: $0.6 /M
Output: $2.4 /M

Parakeet TDT 0.6B v3

NVIDIA

Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across all official EU languages and achieves a 6.34% average word error rate on the HuggingFace Open ASR Leaderboard. Returns transcribed text with punctuation and segment timestamps.

Context: -
Max output: -
Released: 2026-05-27

Input: $25 /M

Nemotron 3 Super

NVIDIA

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.

Context: 262.1K
Max output: -
Released: 2026-03-11

Input: $0.08 /M
Output: $0.45 /M

Nemotron 3 Nano 30B A3B

NVIDIA

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.

Context: 262.1K
Max output: -
Released: 2025-12-14