Nemotron Cascade 2
on-demand
Hosted on our own DGX Spark in Austria, available through an OpenAI-compatible API.
69
Logic Index · no budget field
46 t/s
tokens per second here
€ 0.75 / € 3
euros per M tokens, input / output
10M free tokens
Try Nemotron Cascade 2 for free
Every new account starts with 10M free tokens, usable for this and every other model. No card, no subscription.
Fact sheet
- Model name in the API
- nemotron-cascade-2
- Size
- 32B dense (Q4_K_M)
- Context
- 256K
- Input
- Text
- Capabilities
- ToolsReasoning
- License
- NVIDIA Open Model License
- Tier
- Reasoning
- Hosting
- loaded on demand
Call
OpenAI-compatible. The alias works as model name too.
{
"model": "nemotron-cascade-2",
"messages": [ … ]
}
Logic Index
All models in the Logic Index →By test area
Reasoning chains
78
Logic vs. world knowledge
80
Logic grid puzzles
50
Consistency: same answer in every run for 87% of tasks.