Context lengths are 256,000 tokens on nemotron-3-nano-30b-a3b-free and 1,000,000 tokens on nemotron-3-ultra-550b-a55b-free.
nemotron-3-nano-30b-a3b-freenemotron-3-ultra-550b-a55b-freeNVIDIA Nemotron 3 Nano 30B A3B is a highly efficient small language Mixture of Experts (MoE) model developed by Nvidia. Designed to help developers build specialized agentic AI systems, it delivers exceptional compute efficiency and accuracy. Additionally, it features an impressive context length of 256,000 tokens to support extensive data processing.
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model featuring an extensive 1,000,000-token context length. Built on a hybrid Transformer-Mamba mixture-of-experts (MoE) architecture, it operates with 55B active parameters out of a total of 550B parameters. This advanced structure is designed to support sophisticated reasoning and complex task orchestration.
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Daily traffic served through AIHubMix — how demand for each model is trending.
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
nemotron-3-nano-30b-a3b-free accepts 256,000 and nemotron-3-ultra-550b-a55b-free accepts 1,000,000 input tokens.
nemotron-3-nano-30b-a3b-free accepts text input and supports reasoning, tool calling and long context; nemotron-3-ultra-550b-a55b-free accepts text input and supports reasoning, tool calling and long context.
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Related model match-ups readers also look at.
AIHubMix