Context
262K
Input
$0.05/M
Output
$0.20/M
Aliases:nemotron-3-nanonvidia-nemotron-3-nano-30b-a3bnemotron-3-nano-a3b
NVIDIA's efficient hybrid MoE model combining Mamba-2 and Transformer layers, with 30B total and 3.5B active parameters. Reasoning can be toggled on or off, and it handles English, code and several European and Asian languages.
deepinfra/nemotron-3-nano-30bQuantfp4
- Input
- $0.05/M
- Output
- $0.20/M
- Context
- 262K
- Max out
- 228K
- Cache read
- $0.03/M
- Cache write
- $0.05/M
- Thinking out
- $0.20/M