nemotron-lightning-3.5-30b-a3b
Nemotron-Lightning-3.5-30B-A3B is a 30B-parameter Mixture-of-Experts language model (3B active) from NVIDIA's Nemotron-H family, built on a hybrid Mamba-Transformer architecture for efficient long-context inference.
text → text · no single maker — the market carries it
$0.05→$0.2per Mtok in / out
Fireworks AI
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| Fireworks AI 0 ways | $0.05per Mtok in$0.2per Mtok out$0.01per Mtok cached | |
| Fireworks AI aggregatornot on the seller's list today | standard | $0.05per Mtok in$0.2per Mtok out$0.01per Mtok cachedraw.githubusercontent.com · read 2026-08-27 |
| Requesty aggregator | fireworks | $0.05per Mtok in$0.2per Mtok out$0.01per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
About
nemotron-lightning-3.5-30b-a3b — a text model.
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 evaluate.
Every current figure
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 262,144 tokens
- Published
- August 2026
- Parameters
- 30 billion · read from its own name, the total of a mixture
- Licence
- not read
Known as 1 name
fireworks/nemotron-lightning-3.5-30b-a3b