NVIDIA: Nemotron 3.5 Lightning
Provider: nvidia · nvidia/nemotron-3.5-lightning
How NVIDIA: Nemotron 3.5 Lightning pricing compares
At $0.2 / 1M output tokens, NVIDIA: Nemotron 3.5 Lightning is the 1st-cheapest of 5 nvidia models we track. It's cheaper than 92% of the 392 paid models on computetrail (33rd-cheapest overall). Output costs 2.5× its input price ($0.08 / 1M in). For a typical 3:1 input-to-output workload that works out to about $0.11 / 1M blended. Reading cached input costs 50% less than fresh input, so prompt caching cuts repeat-context cost sharply. Its 262,144 tokens context window ranks 169th-largest of 392 models with a published limit.
Output price history
Across 16 daily snapshots since 2026-08-12, the output price has fallen 20.0% — from $0.25 to $0.2 / 1M.
Similar-priced models
| Model | Provider | Output $/1M | Context |
|---|---|---|---|
| NVIDIA: Nemotron 3 Nano 30B A3B | nvidia | $0.2 | 262,144 |
| Mistral: Mistral Small 3.2 24B | mistralai | $0.2 | 131,072 |
| Meta: Llama 3.2 1B Instruct | meta-llama | $0.201 | 60,000 |
| Qwen: Qwen3 14B | qwen | $0.24 | 131,072 |
| Amazon: Nova Lite 1.0 | amazon | $0.24 | 300,000 |
| DeepSeek: DeepSeek V4 Flash 0423 | deepseek | $0.159 | 1,048,576 |
Prices are recorded daily from public provider data via OpenRouter and normalized to USD per 1M tokens. See methodology.