Nemotron 3.5 Lightning 30B A3B
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...
Context
1,048,576
Max output
1,048,576
Input / 1M
$0.05
Output / 1M
$0.18
Providers
6
01Profile
Profile
Released
2026-08-11
Last updated
2026-08-11
Knowledge cutoff
—
Weights
Open
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 7 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2026-08-11
2026-09-11Price cutkiloinput / 1M$0.08→ $0.07
2026-09-11Price cutkilooutput / 1M$0.20→ $0.18
2026-09-11Addednano-gptoffering→ new
2026-09-02Addednebiusoffering→ new
2026-08-28ContextkiloMax output131,072→ 235,929
2026-08-28ContextkiloMax output235,929→ 131,072
2026-08-28Price upopenrouterinput / 1M$0.08→ $0.10
2026-08-28Price cutopenrouterinput / 1M$0.10→ $0.08
2026-08-28Price upopenrouteroutput / 1M$0.20→ $0.25
2026-08-28Price cutopenrouteroutput / 1M$0.25→ $0.20
2026-08-28ContextopenrouterMax output131,072→ 235,929
2026-08-28ContextopenrouterMax output235,929→ 131,072