About
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...
Related Models
Pricing
Input
$0.25
per 1M tokens
Output
$1.00
per 1M tokens
Blended
$0.44
per 1M tokens
Cheaper than 54% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.44
Monthly
$13.13
vs. Similar Models
Claude Opus 4.5 (Reasoning)Q:-0.2
$10.00+2186%
DeepSeek V4 Pro (Reasoning, High Effort)Q:-0.2
$0.54+24%
DeepSeek: DeepSeek V4 FlashQ:-0.7
$0.11-74%
MiMo-V2-ProQ:-0.7
$1.50+243%
Performance
86
tokens/sec
Faster than 47% of models
0.99
seconds
Faster than 57% of models
24.14
seconds
Faster than 21% of models
Market Median
94 tok/s
8% slower
Median TTFT
1.11s
11% faster
Throughput/Dollar
197
tok/s per $/1M
Speed Comparison
Ring-flash-2.0
86 tok/s+0%
MiMo-V2.5
86 tok/s-0%
Reka Flash (Sep '24)
86 tok/s-0%
Context Window
262K
tokens
Larger than 62% of models
Max Output
262K
tokens
100% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
89.2%
HLE
32.4%
LiveCodeBenchNot evaluated
SciCode
41.8%
TerminalBench HardNot evaluated
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
66.2%
Long Context Recall
67.7%
Tau2
81.6%
Market AverageTop Score
