nemotron-3-nano-30b-a3b

1315 Score third-party Elo · arena.ai / LMArena ?

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

LLM & Generative AI 1 model 2 listings snapshot Oct 14, 2026, 12:54 AM

Platforms

click a card to open the detail table

Cheapest Novita no official benchmark Input$0.050 Output$0.200 per 1M tokens Fastest OpenRouter lowest p50 latency on this board 128.1 ms p50 Most free quota — largest published free allowance — free tier

Model variants

W3r9 dedup — same model + identical tags merge; prices are listed per billing form

Model	Provider	Tags	Input /1M	Output /1M
nvidia/nemotron-3-nano-30b-a3b	OpenRouter	30b256k contextreasoning	$0.060	$0.240
nvidia/nemotron-3-nano-30b-a3b	Novita	30b	$0.050	$0.200

Capabilities

official design_arena & architecture metadata

Design Arena Elo official design_arena benchmark (OpenRouter)

No official Design Arena benchmark from this provider. Showing official architecture metadata only.

Input / Output modalities modality: text->text

text in+out

Platform details

per provider

provider	model	Input /1M	Output /1M	Latency ?	Official $/1M	Availability	Data time
Novita	nvidia/nemotron-3-nano-30b-a3b	$0.050	$0.200	—	—	—	2026-10-14 00:54:15
OpenRouter	nvidia/nemotron-3-nano-30b-a3b	$0.060	$0.240	128.1 ms	—	100% available	2026-10-14 00:43:21
Together	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16	$0	$0	—	—	—	2026-10-14 00:53:13

3 rows · snapshot 2026-10-14 00:54:15 · from data/public/prices.json + measurements.json