Cline offers NVIDIA Nemotron 3.5 Lightning free for a limited time

Cline has added NVIDIA's open Nemotron 3.5 Lightning to its free model list. Anyone with a Cline account can pick it in the IDE extension or CLI and use it at no cost until the free quota runs out.

It is a small, fast model that suits high-volume agent subtasks, code search, and long-document Q&A.

What you can use

The model name is Nemotron 3.5 Lightning, and the model ID is nvidia/nemotron-3.5-lightning-free. It is part of Cline's rotating, limited-time free model promotion with a usage quota, and the free lineup changes over time.

After the free quota is used up, you can continue with ClinePass at $9.99 a month, or switch to Cline usage-billing.

Specs and public benchmarks

Nemotron 3.5 Lightning is an open-weight mixture-of-experts model with 30B total parameters and 3B active per token. It interleaves Mamba-2 layers, MoE layers, and a few attention layers, supports up to 1M tokens of context, and lets you turn reasoning on or off.

In NVIDIA's evaluations it scores 51.56% on SWE-bench Verified, 24.58% on Terminal-Bench 2.1, 85.37 on PinchBench, and 75.44% on GPQA Diamond. It works well for everyday small edits and subtasks, while bigger models remain the safer choice for complex coding work.

How to use it

1. Open the Cline IDE extension or CLI and sign in with your Cline account.
2. Set the API provider to Cline (usage-billing), then pick the FREE-tagged Nemotron 3.5 Lightning, or select nvidia/nemotron-3.5-lightning-free directly.
3. During promotional periods, free models are also available under the ClinePass provider.

Free models are not available through the Cline API, only in the IDE extension and CLI. Free usage may be used to help improve model performance and quality.

Details: Cline Free Models and the Nemotron 3.5 Lightning model card.

Other free ways to use it

If you want plain API access, Vercel AI Gateway and OpenRouter also offer Nemotron 3.5 Lightning for free.