NVIDIA
Models published by NVIDIA, available through the AnyRouter API. Each can route across multiple upstream providers for availability and price.
NVIDIA's Mixture-of-Experts model with 120B total parameters and 12B active, optimized for efficient inference with strong reasoning capabilities.
NVIDIA Nemotron-3-Embed-1B is a 1.14B-parameter multilingual text embedding model (2048 dimensions, 34 languages) for semantic search, retrieval, and RAG. Built on Ministral-3-3B-Instruct; state-of-the-art on multilingual retrieval benchmarks (MMTEB 71.05, RTEB 72.38). Served via NVIDIA NIM.
A compact 30 billion parameter model from NVIDIA's Nemotron-3 family, tuned for fast, efficient text generation and understanding tasks.
NVIDIA Nemotron 3 Nano Omni 30B-A3B (reasoning) is a multimodal MoE model unifying video, audio, image, and text understanding for enterprise Q&A, summarization, transcription, OCR
A 120 billion parameter model from NVIDIA's Nemotron-3 family, optimized for efficient text generation and understanding tasks.
NVIDIA Nemotron-3-Ultra-550B-A55B is a 550B parameter (55B active) frontier model built on a LatentMoE hybrid architecture combining Mamba-2, MoE, and Attention with Multi-Token Prediction. Features a 1M token context window, configurable reasoning mode (enable_thinking), and strong multilingual support across English, French, Spanish, Italian, German, Japanese, Korean, Hindi, Brazilian Portuguese, and Chinese. Best suited for complex agentic workflows, long-context analysis, tool use, and high-stakes RAG.
A compact 4B-parameter multimodal guardrail model fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, returning a safe/unsafe classification, safety category labels, and optional reasoning. Served via NVIDIA NIM.
NVIDIA Nemotron 3.5 Lightning 30B A3B is a sparse MoE chat model optimized for low-latency agentic workloads on NVIDIA NIM.
NVIDIA Nemotron 3.5 Super VL is a vision-language model for reasoning, coding, tool use, document understanding and video understanding. A hybrid Mamba-2 and Transformer mixture-of-experts with 120B total and 12B active parameters, and up to 1M tokens of context.
NVIDIA Nemotron Parse 2.0 is a document-understanding VLM: page image in, structured text out (markdown, layout classes, bounding boxes, reading order). Served via NVIDIA NIM OpenAI-compatible /v1/chat/completions. Not image generation.
NVIDIA's Riva Translate 4B Instruct v2, a compact 4B-parameter instruction-tuned model optimized for high-quality neural machine translation across 30+ languages. Served via NVIDIA NIM.
NVIDIA Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads while supporting up to 1M token context. Designed for advanced function calling, structured output, and complex reasoning tasks.