Nemotron Cascade 2 30B A3B is a reasoning-optimized language model from NVIDIA, designed for efficient inference with strong reasoning capabilities across complex tasks.
256K ctx·$0.14/M in·$0.8/M out·Updated Jul 17, 2026Private
NVIDIA
nvidia/ · 5 models
Access 5 NVIDIA models through AnonRouter's privacy-first gateway, including Nemotron Cascade 2 30B A3B, NVIDIA Nemotron 3 Nano 30B, and NVIDIA Nemotron 3 Ultra. Compare pricing, context windows, and capabilities across NVIDIA's text, audio, embeddings routes — every request anonymized, with no payload logging.
Models
5
Modalities
3
Text, Audio, Embeddings
From (input)
$0.0125
per 1M tokens
Max context
256K
Private routes
5 / 5
not anonymous-only
Catalog by modality
5 routesText3Audio1Embeddings1
NVIDIA models5
NVIDIA Nemotron 3 Nano 30B is a compact and efficient language model from NVIDIA, optimized for fast inference while maintaining strong performance across diverse tasks.
128K ctx·$0.075/M in·$0.3/M out·Updated Jul 17, 2026Private
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…
256K ctx·$0.625/M in·$3.125/M out·Updated Jul 17, 2026Private
Embedding model for semantic search and retrieval, served through Venice.
33K ctx·$0.0125/M in·$0.0125/M out·Updated Jul 17, 2026Private
Speech-to-text transcription model served through Venice.
– ctx·$0.006/min·–·Updated Jul 17, 2026Private