Compare Models
Run side-by-side checks for pricing, context window, and latency.
nemotron-3-120b-a12b
nvidia
NVIDIA Nemotron 3 Super is a hybrid MoE model with leading accuracy for multi-agent applications and specialized agentic AI systems.
- Context window
- 256,000 tokens
- Input cost
- $0.50 / 1M
- Output cost
- $1.50 / 1M
- Latency (p50)
- —
