Nemotron 3.5 Lightning
loaded
fastswift
Hosted on our own DGX Spark in Austria, available through an OpenAI-compatible API.
76
Logic Index · budget 30,000
111 t/s
tokens per second here
€ 0.25 / € 1
euros per M tokens, input / output
10M free tokens
Try Nemotron 3.5 Lightning 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-3.5-lightning
- Size
- 30B / 3B MoE (NVFP4 (ModelOpt, MIXED_PRECISION))
- Context
- 256K
- Input
- Text
- Capabilities
- ToolsReasoning
- License
- OpenMDW-1.1
- Tier
- Fast
- Hosting
- always loaded
Call
OpenAI-compatible. The alias works as model name too.
{
"model": "fast",
"thinking_token_budget": 30000,
"messages": [ … ]
}
This thinking budget is the one the Logic Index was reached with. Without the field, our default for short answers applies.
Logic Index
All models in the Logic Index →By test area
Reasoning chains
91
Logic vs. world knowledge
97
Logic grid puzzles
40
Consistency: same answer in every run for 94% of tasks.
Index by thinking budget
Speed over time
Operations of the Sparks →Tokens per second from our nightly measurement. Latest: 111 t/s.