nex-agi Open weights Vision Reasoning

Nex-N2-Pro pricing & benchmarks

Released Jun 8, 2026 · served by 2 providers · ranked #26 by intelligence in our index

Input / 1M tokens$0.250

Output / 1M tokens$1.00

Context window262K

Cached input$0.025

Intelligence index41.0

Coding index59.1

Agentic index31.0

1M in + 300K out$0.55

What Nex-N2-Pro is

Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...

Model ID: nex-agi/nex-n2-pro
Modality: text+image->text
Tool calling: supported · Structured output: not supported
Weights: nex-agi/Nex-N2-Pro on Hugging Face

Providers and prices for Nex-N2-Pro

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

Provider	Input	Output	Context	Quant	Uptime 24h	Throughput
Nex AGIcheapest	$0.250	$1.00	262K	fp8	96.5%	—
SiliconFlow	$0.500	$2.50	262K	—	96.0%	—

Nex-N2-Pro benchmark results

Design Arena head-to-head results, as reported through the OpenRouter model API.

Category	Arena	Rank	Elo	Win rate
svg	models	#11	1253	52.6%
3d	models	#16	1308	55%
dataviz	models	#19	1278	53%
gamedev	models	#24	1280	51.3%
codecategories	models	#25	1275	51.4%
uicomponent	models	#31	1261	49.1%
website	models	#31	1259	49.3%
asciiart	models	#48	1131	37.3%

Cheaper models in the same class

Models scoring within 4 points of Nex-N2-Pro on the Intelligence Index, but with a lower output price.

Nemotron 3 Ultra (free) Free / 1M out · index 37.8 DeepSeek V4 Flash $0.179 / 1M out · index 40.3 Hy3 preview $0.210 / 1M out · index 41.2 MiMo-V2.5 $0.224 / 1M out · index 37.2 GPT-5.4 Nano $0.625 / 1M out · index 38.2

Compare Nex-N2-Pro head-to-head

Claude Opus 5 vs Nex-N2-Pro price, context and benchmarks side by side Claude Fable 5 vs Nex-N2-Pro price, context and benchmarks side by side GPT-5.6 Sol vs Nex-N2-Pro price, context and benchmarks side by side Kimi K3 vs Nex-N2-Pro price, context and benchmarks side by side Claude Opus 4.8 vs Nex-N2-Pro price, context and benchmarks side by side GPT-5.6 Terra vs Nex-N2-Pro price, context and benchmarks side by side

FAQ

How much does the Nex-N2-Pro API cost?

$0.250 per 1M input tokens and $1.00 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.55.

Is Nex-N2-Pro free?

No. It is a paid model starting at $0.250 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Nex-N2-Pro?

Nex AGI at $0.250 input / $1.00 output per 1M tokens (fp8 quantization).

Can I self-host Nex-N2-Pro?

Yes — weights are published as nex-agi/Nex-N2-Pro on Hugging Face, so you can run it on your own hardware.