NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 vs Mercury 2.5

API pricing, benchmark indices and specs — updated 19 October 2026.

nvidia · A · Open weights

Params

31.6 B

Context

262,144

30d

743 K

inception · B · API-only

Input / 1M

$0.04

Output / 1M

$0.15

AA index

12.3

proprietary · 260K context

Specification comparison

Differences are highlighted; identical values are muted.

Specification	NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16	Mercury 2.5
Deployment	Open weights · also via API	API-only (closed weights)
Parameters	31.6 B	n/a — API-only
Architecture	NemotronHForCausalLM	n/a — API-only
Context length	262,144	260,000
Licence	other	Proprietary
Commercial use	Unknown	Per API terms
Languages	6	n/a — API-only
Downloads 30d	742,789	n/a — API-only
Downloads all time	1.5 M	n/a — API-only
Quantizations on the Hub	SAFETENSORS	n/a — API-only
Gated	No	n/a — API-only
First seen on the Hub	2026-08-01	n/a — API-only
API input price / 1M tokens	$0.07	$0.04
API output price / 1M tokens	$0.20	$0.15
Est. cost per 1M input + 1M output tokens	$0.27	$0.19
Cached input / 1M tokens	$0.04	$0.004
AA Intelligence Index	12.9	12.3
AA Coding Index	26.8	—
AA Agentic Index	3.5	—
Max output tokens	235,929	65,536
API providers	4	1
Tool calling	Yes	Yes
Reasoning mode	Yes	Yes

Estimated cost of 1M input + 1M output tokens via OpenRouter

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 $0.27

Mercury 2.5 $0.19

Mercury 2.5 is 1.4× cheaper at list price.

On RTX 4090 · 24 GB · 8K context unless noted

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · fp16 @ 256K ctx 224.5 GB / 24 GB

❌ Won’t fit