NVIDIA: Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3b
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
Modalities
In / Out Price
$0.06 / $0.24 per 1M
Context
262K
Released
Dec 14, 2025
Knowledge Cutoff
—
Providers
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
 Novitafp4 | 262K | $0.05 | $0.20 | — | — | — | 100.00% |
 Nebiusfp8 | 262K | $0.06 | $0.24 | — | — | — | 100.00% |