NVIDIA Nemotron 3 Nano is an open small reasoning model optimized for fast, cost-efficient inference in agentic and production workloads. Built with a hybrid Mixture-of-Experts (MoE) and Mamba-Transformer architecture, it delivers strong multi-step reasoning, high token throughput, stable latency with predictable cost, and efficient deployment for agent-based systems. Designed for real-world AI systems where reasoning can generate significantly more tokens per prompt, Nemotron Nano reduces co...
function_callinghttps://api.deepinfra.com/v1/openai/v1/chat/completions| Model | Context | Max out | Pricing |
|---|---|---|---|
| NVIDIA-Nemotron-Nano-9B-v2 | 131K | — | $0.04$0.16 |
| Nemotron-3-Nano-30B-A3B | 262K | — | $0.05$0.2 |
| NVIDIA-Nemotron-3-Super-120B-A12B | 262K | — | $0.09$0.4 |
| NVIDIA-Nemotron-Nano-12B-v2-VL | 131K | — | $0.2$0.6 |
/v1/models/deepinfra/nvidia/Nemotron-3-Nano-30B-A3BNVIDIA Nemotron 3 Nano is an open small reasoning model optimized for fast, cost-efficient inference in agentic and production workloads. Built with a hybrid Mixture-of-Experts (MoE) and Mamba-Transformer architecture, it delivers strong multi-step reasoning, high token throughput, stable latency with predictable cost, and efficient deployment for agent-based systems. Designed for real-world AI systems where reasoning can generate significantly more tokens per prompt, Nemotron Nano reduces co...