NVIDIA: Nemotron 3 Ultra
nvidia/nemotron-3-ultra-550b-a55b
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...
Modalities
Text
In / out price
₩1,097 / ₩5,484
1M
Context
262.14K
Released
Jun 4, 2026
Pricing
Prices are quoted in Korean won. Changes to the exchange rate or margin show up immediately.
| Input (prompt) | ₩1,097 / 1M |
| Output (completion) | ₩5,484 / 1M |
| Cache read | ₩329 / 1M |
| Cache write | — |
1,000 input tokens plus 1,000 output tokens costs about ₩6.58.