Nex AGI: Nex-N2-Pro

Image input Text input Text output
Author's Description

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...

Key Specifications
Cost
$$$$
Context
262K
Parameters
397B (Rumoured)
Released
Jun 08, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Logprobs Top Logprobs Include Reasoning Reasoning Temperature Max Tokens Top P
Features

This model supports the following features:

Reasoning
Performance Summary

Nex AGI's Nex-N2-Pro, an agentic mixture-of-experts model built on the Qwen3.5 architecture with 17B active parameters, demonstrates competitive response times, ranking in the 44th percentile for speed. Its pricing is moderate, placing it in the 35th percentile. Notably, the model exhibits exceptional reliability with a 97% success rate across benchmarks, indicating consistent operational stability. Performance across benchmarks reveals a mixed profile. Nex-N2-Pro excels in General Knowledge and Ethics, achieving perfect 100% accuracy in both, often being the most accurate model at its price point and speed. It also shows strong capabilities in Email Classification (99% accuracy), Reasoning (96% accuracy), and Coding (93% accuracy), performing well above average. Instruction Following and Mathematics also demonstrate solid performance at 75% and 93% accuracy respectively. However, a significant weakness is observed in Hallucinations, where it scores only 68% accuracy, indicating a tendency to provide answers rather than acknowledge uncertainty, placing it in the 14th percentile for this metric.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.5
Completion $2.5
Input Cache Read $0.25

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Nex AGI
Nex AGI | nex-agi/nex-n2-pro 262K $0.5 / 1M tokens $2.5 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by nex-agi