We just added
@NVIDIA Nemotron 3.x to DeepInfra — Day 0.
Two open and highly efficient models, live now:
→ Nemotron 3 Ultra: Frontier reasoning for long-running agents with, up to 5x faster inference and up to 30% lower cost
→ Nemotron 3.5 Content Safety: 4B multimodal, multilingual safety model with custom policy support, reasoning traces, and coverage across, 23 safety categories for enterprise AI guardrails
→ Nemotron 3.5 ASR:(Coming soon) 0.6B streaming model with ~40 language-locales.
Built for agentic AI. Same API as everything else on DeepInfra.