NVIDIA: Nemotron 3 Ultra (batch)
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...
Everything else
| Max output | — |
|---|---|
| Input / 1M | $0.3 |
| Output / 1M | $1.80 |
| Cache read / 1M | $0.1 |
| Cache write / 1M | — |
| 1M in + 1M out | $2.10 |
| Takes | text |
| Returns | text |
| Tools | yes |
| Reasoning | optional · high, medium |
| Open weights | yes |
| Released | 2026-06-04 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | nvidia/nemotron-3-ultra-550b-a55b:batch |
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.