Nemotron 3.5 Lightning
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a large language model (LLM) trained by NVIDIA. The model employs a hybrid Mixture-of-Experts architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers.
text → text · made by NVIDIA
Free
Offered at no charge, which is not the same as cheap: a free lane carries a rate limit and can be withdrawn. The prices above are what you pay when it is not available to you.
- OpenRouter
Sold by 12 ways
| Seller | Lane | Rate |
|---|---|---|
| OpenRouter 6 ways | $0.08per Mtok in$0.2per Mtok out$0.04per Mtok cached | |
| OpenRouter aggregator | free | $0per Mtok in$0per Mtok outopenrouter.ai · read 2026-09-16 |
| OpenRouter aggregator | darkbloom/int4 | $0.065per Mtok in$0.18per Mtok outopenrouter.ai · read 2026-09-14 |
| OpenRouter aggregator | coreweave/bf16 | $0.07per Mtok in$0.2per Mtok out$0.04per Mtok cachedopenrouter.ai · read 2026-09-15 |
| OpenRouter aggregator | standard | $0.08per Mtok in$0.2per Mtok out$0.04per Mtok cachedopenrouter.ai · read 2026-08-29 |
| OpenRouter aggregator | deepinfra/bf16 | $0.08per Mtok in$0.2per Mtok out$0.04per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | phala | $0.08per Mtok in$0.2per Mtok out$0.04per Mtok cachedopenrouter.ai · read 2026-09-12 |
| ElectronHub aggregator | standard | $0.01per Mtok in$0.05per Mtok outapi.electronhub.ai · read 2026-09-16 |
| Vercel AI Gateway aggregator | standard | $0.05per Mtok in$0.2per Mtok out$0.01per Mtok cachedai-gateway.vercel.sh · read 2026-08-25 |
| Nebius Token Factory aggregator | standard | $0.06per Mtok in$0.24per Mtok outtokenfactory.nebius.com · read 2026-08-25 |
| Nous Research aggregatornot on the seller's list today | resold | $0.064per Mtok in$0.16per Mtok out$0.032per Mtok cachedinference-api.nousresearch.com · read 2026-08-25 |
| Nous Research aggregator | standard | $0.065per Mtok in$0.18per Mtok out$0.032per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| DeepInfra aggregator | standard | $0.08per Mtok in$0.2per Mtok outapi.deepinfra.com · read 2026-08-25 |
Measured 3 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 105thof 143 | Artificial Analysis · Agentic Index | Index | 6.1 |
| 135thof 184 | Artificial Analysis · Coding Index | Index | 26.8 |
| 154thof 302 | Artificial Analysis · Intelligence Index | Artificial Analysis Intelligence Index | 14 |
About
Nemotron 3.5 Lightning — a text model from NVIDIA, sold by 6 companies from $0.01 in and $0.05 out per million tokens, placed 154th of 302 on Artificial Analysis · Intelligence Index.
It takes text and returns text, with a context window of 262,144 tokens. It was published in August 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under chat. Six companies sell it. The cheapest is $0.01 in and $0.05 out per million tokens at ElectronHub. Beside the standard rate there are regional and separately routed lanes. It has been measured on 3 boards, and stands best at 154th of 302 on Artificial Analysis · Intelligence Index.
Every current figure
- Maker
- NVIDIA
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 262,144 tokens
- Published
- August 2026
- Sellers
- 6
- Maker's own price
- not read
- Price
- $0.01 in and $0.05 out per million tokens — ElectronHub
- Boards
- 3
- Best place
- 154th of 302 — Artificial Analysis · Intelligence Index
Known as 3 names
nvidia/NVIDIA-Nemotron-3.5-Lightningnvidia/Nemotron-3_5-Lightningnvidia/nemotron-3.5-lightning