Context
262K
Input
$0.30/M
Output
$2.40/M
Aliases:nemotron-3nemotron-3-120b-a12bnvidia-nemotron-3-120b-a12bnemotron-3-nano-120b-a12b
NVIDIA's hybrid MoE model with leading accuracy for multi-agent applications and specialized agentic AI systems.
crusoe/nemotron-3-120bQuantUnspecified
- Input
- $0.30/M
- Output
- $2.40/M
- Context
- 262K
- Max out
- 66K
- Cache read
- $0.15/M
- Cache write
- $0.30/M
- Thinking out
- $2.40/M