NVIDIA: Nemotron 3.5 Lightning
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...
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↓ lowerOutput $0.18 → $0.12
- ↓ lowerInput $0.039 → $0.025
- ↓ lowerOutput $0.2 → $0.18
- ↓ lowerInput $0.05 → $0.039
- ↑ higherOutput $0.18 → $0.2
- ↑ higherInput $0.04 → $0.05
- ↓ lowerOutput $0.2 → $0.18
- ↓ lowerInput $0.05 → $0.04
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (5 omitted). Show free/$0 listings.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestnvidia/nemotron-3.5-lightning | Kilo Gateway | $0.025 | $0.12 | $0.0125 | 262K |
| models.devnvidia/nemotron-3.5-lightning | NanoGPT | $0.05 | $0.2 | $0.01 | 1M |
| models.devnvidia/nemotron-3.5-lightning | Vercel AI Gateway | $0.05 | $0.2 | $0.01 | 262K |
| models.devnvidia/nemotron-3.5-lightning:thinking | NanoGPT | $0.05 | $0.2 | $0.01 | 1M |
| models.devnvidia/Nemotron-3_5-Lightning | Nebius | $0.06 | $0.24 | $0.06 | 1.0M |
| LiteLLMnvidia/Nemotron-3_5-Lightning | N/A | $0.06 | $0.24 | $0.006 | N/A |
| LiteLLMNemotron-3_5-Lightning | N/A | $0.06 | $0.24 | $0.006 | N/A |
| OpenRouternvidia/nemotron-3.5-lightning | OpenRouter | $0.07 | $0.2 | $0.04 | 262K |
| models.devTEE/nemotron-3.5-lightning | NanoGPT | $0.08 | $0.2 | $0.04 | 262K |
| LiteLLMnvidia/NVIDIA-Nemotron-3.5-Lightning | N/A | $0.08 | $0.2 | $0.04 | N/A |
| LiteLLMNVIDIA-Nemotron-3.5-Lightning | N/A | $0.08 | $0.2 | $0.04 | N/A |
| LiteLLMdeepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning | N/A | $0.08 | $0.2 | $0.04 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence12.9i
- AA coding26.8i
- AA agentic3.5i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.