All models
NVIDIA
Nemotron 3.5 Lightning fastruns locally
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...
Input / 1M
$0.070
USD per million tokens
Output / 1M
$0.20
USD per million tokens
Est. cost / token
$0.000000102
$0.10 per 1M, 3:1 mix
Context window
262K
max output 236K
Major features
Open weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context3
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 16.4 GB |
| Q3_K_M | fair | 18.7 GB |
| Q4_K_Mrecommended | good | 22.8 GB |
| Q5_K_M | very good | 26.1 GB |
| Q6_K | excellent | 29.7 GB |
| Q8_0 | near-lossless | 37.8 GB |
| F16 | lossless | 68.9 GB |
Estimates. Mixture-of-experts: memory covers all parameters; only the active ones are used per token, so it runs faster than its size suggests.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.070 | $0.20 | $0.040 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.070
- Output
- $0.20
- Cached input
- $0.040
- Blended (3:1)
- $0.10
Details
- Company
- NVIDIA
- Version
- 3.5
- Family
- Nemotron
- Released
- 2026-08-11
- Parameters
- 31.6B (3B active)
- Max output
- 236K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 46 min ago