modelgrep
N

Nex AGI: Nex-N2-Pro

nex-agi/nex-n2-pro

31st smartest of 161ReasoningToolsVision
Use via OpenRouter ↗
Intelligence
41.0
31st of 161
Design Elo
1306
3D
Speed
59
149th fastest
Latency
1.0s
first token
Input price
$0.250
104th cheapest
Context
262K
262K max out

How it compares

Smarter than81%
of all ranked models
Faster than53%
of all ranked models
Cheaper than66%
of all ranked models

Overview

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...

Benchmarks

independent · Artificial Analysis & Design Arena
Artificial Analysis91th percentile
Intelligence Index
41.0
Coding Index
59.1
Agentic Index
31.0
GPQA Diamond
89%
Humanity's Last Exam
32%
SciCode
42%
Tau²-Bench (agentic)
82%
Design Arena · Elo2,720 tournaments
3D
1306
Data Viz
1271
UI Component
1259
Game Dev
1259
Website
1249
svg
1247

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Nex AGIfp8$0.250$1.0099.3%
SiliconFlow$0.500$2.50

Specifications

Context window262K
Max output262K
Knowledge cutoff
Input modalitiestext, image
Output modalitiestext
Prompt caching
Cache read price$0.025/M
ModeratedNo

Nex-N2-Pro FAQ

How much does Nex-N2-Pro cost?

Nex-N2-Pro costs $0.250 per million input tokens and $1.00 per million output tokens via OpenRouter, making it 104th cheapest of 307 paid models.

How smart is Nex-N2-Pro?

Nex-N2-Pro scores 41.0 on the Artificial Analysis Intelligence Index, ranking 31st of 161 benchmarked models, with a GPQA Diamond score of 89%.

How fast is Nex-N2-Pro?

Nex-N2-Pro generates around 59 tokens per second with 1.0s time-to-first-token (p50), the 149th fastest tracked model.

What is Nex-N2-Pro's context window?

Nex-N2-Pro supports a 262K-token context window and can output up to 262K tokens. It accepts text, image input.

Compare head-to-head