Skip to content
NINJA

Nemotron 3.5 Lightning

Released by NVIDIA on 11 Aug 2026.

API id nvidia/nemotron-3.5-lightning

Input price
$0.07 / 1M tokens
Output price
$0.20 / 1M tokens
Context window
262K tokens
Longest reply
236K tokens

About this model

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...

Description from the model’s public catalogue listing.

Capabilities

Reads
Text
Writes
Text
Reasoning mode
Yes
Tool calling
Yes
Open weights
Yes
Cached input
$0.04 / 1M tokens

What it would cost

At list price, without caching or batch discounts.

1,000 chat replies2K tokens in, 500 out each
$0.24
Summarise 100 long reports50K tokens in, 1K out each
$0.37
A coding agent’s working day20M tokens in, 1M out
$1.60
Price your own workload on every model

Price history

Per 1M tokens, input then output. Tracked since 30 Sept 2026.

10 Oct 2026
$0.047 → $0.07+49%$0.13 → $0.20+49%
10 Oct 2026
$0.07 → $0.047-33%$0.20 → $0.13-33%
9 Oct 2026
$0.047 → $0.07+49%$0.13 → $0.20+49%
9 Oct 2026
$0.049 → $0.047-4%$0.14 → $0.13-4%
7 Oct 2026
$0.06 → $0.049-18%$0.16 → $0.14-12%
5 Oct 2026
$0.059 → $0.06+1%$0.17 → $0.16-6%
3 Oct 2026
$0.06 → $0.059-1%$0.16 → $0.17+6%
2 Oct 2026
$0.059 → $0.06+1%$0.17 → $0.16-6%
1 Oct 2026
$0.06 → $0.059-1%$0.16 → $0.17+6%

Alternatives at a similar price

From other labs, priced within about 40% of Nemotron 3.5 Lightning, with a comparable context window.

More from NVIDIA

See all