Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads
Specification
most-agreed values
Context
262K
Max output
262K
Released
2026-08-11
Knowledge cutoff
2025-09
Retires
2026-11-07
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.05
Output
$0.20
Cache read
$0.01
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Priority input | fireworks_ai | $0.0625 |
| Priority output | fireworks_ai | $0.25 |
Available from 3 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| fireworks_ai | $0.05 | $0.20 | $0.01 | — | 262K | 33K | 2026-11-07 |
| fireworks-ai · accounts | $0.05 | $0.20 | $0.01 | — | 262K | 262K | — |
| requesty | $0.05 | $0.20 | $0.01 | — | 262K | 262K | — |
Other listings of this model
this page is one of them
The corpus files Nemotron 3.5 Lightning 30B A3B under several keys. This page is the nemotron-lightning-3-5-30b-a3b listing. The full record — every host, every price and every benchmark score — is on the main Nemotron 3.5 Lightning 30B A3B page.
More from NVIDIA
most-hosted first