Nemotron 3.5 Lightning
nvidia/nemotron-3.5-lightning
- context
- 262K
- modalities
- text → text
- capabilities
- Tool use, Reasoning, Structured output, Low cost
Overview
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
Providers
- CoreWeaveView CoreWeave
- DarkbloomView Darkbloom
- DeepInfraView DeepInfra
- Io NetView Io Net
- PhalaView Phala
- WaferView Wafer
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| CoreWeave | $0.07 | $0.20 |
| Darkbloom | $0.025 | $0.12 |
| DeepInfra | $0.06 | $0.16 |
| Io Net | $0.0469 | $0.134 |
| Phala | $0.07 | $0.20 |
| Wafer | $0.035 | $0.13 |
CoreWeave
- input / 1M
- $0.07
- output / 1M
- $0.20
Darkbloom
- input / 1M
- $0.025
- output / 1M
- $0.12
DeepInfra
- input / 1M
- $0.06
- output / 1M
- $0.16
Io Net
- input / 1M
- $0.0469
- output / 1M
- $0.134
Phala
- input / 1M
- $0.07
- output / 1M
- $0.20
Wafer
- input / 1M
- $0.035
- output / 1M
- $0.13
Use this model
through Nautili
Route requests to Nemotron 3.5 Lightning through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.