NVIDIA: Nemotron 3 Ultra (free)
— input— output
nvidia/nemotron-3-ultra-550b-a55b:freeDescription
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...
Availability
Pricing for this model is operator-dependent. Open the chat to route a request — the response includes the resolved per-token cost.
Modalities
Input: TextOutput: Text