LLM Reference

Nex-N2 Models by Nex AGI

Nex AGIApache 2.0Open source
2 models2026Up to 262k ctxFrom $0.25/1M input

Details

ResearcherNex AGI
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models2
Released2026
Max context262k

Capabilities

VisionAll models
MultimodalAll models
ReasoningAll models
Function CallingAll models
Tool UseAll models

About

Nex-N2 is an open-weight agentic model family from Nex AGI, built on the Qwen3.5 series. It introduces an Agentic Thinking framework — adaptive reasoning that decides when and how deeply to think — unified across coding, search, and tool use. The family ships in two variants: Nex-N2-Pro (397B MoE) and Nex-N2-mini (35B MoE).

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

2 in view
Nex-N2-ProCurrent

Use when the workload needs coding, 262k context, and reasoning.

2026-06coding262k contextreasoning

Use when the workload needs coding, 262k context, and reasoning.

2026-06coding262k contextreasoning

Release Timeline

1 release group
2026-06
2 current
Nex-N2-mini
coding262k contextreasoning
Current
Nex-N2-Pro
coding262k contextreasoning
Current

Specifications(2 models)

Nex-N2 model specifications comparison
ModelReleasedContextParametersVisionMultimodalReasoningFn CallingTool Use
Nex-N2-Pro2026-06262k397B total, 17B active (MoE)YesYesYesYesYes
Nex-N2-mini2026-06262k35B total, 3B active (MoE)YesYesYesYesYes

Available From(2 providers)

Pricing

Nex-N2 model pricing by provider
ModelProviderInput / 1MOutput / 1MType
Nex-N2-ProOpenRouter$0.25$1Serverless
Nex-N2-ProSiliconFlow$0.5$2.5Serverless

Frequently Asked Questions

What is Nex-N2 used for?
Nex-N2 is used for coding, vision and multimodal work, and reasoning. The family description and listed model capabilities point to those workloads as the best fit.
How does Nex-N2 compare to Claude 3?
Nex-N2 by Nex AGI is strongest where you need coding, while Claude 3 by Anthropic is the closest related family to check for vision and multimodal work. Nex-N2 has 2 listed variants and reaches up to 262k context, while Claude 3 reaches up to 200k context, so compare the specs and pricing tables before choosing a production model.
Which Nex-N2 model should I use?
For the lowest listed input price, start with Nex-N2-Pro through OpenRouter at $0.25/1M input tokens. For the most capable/latest local choice, evaluate Nex-N2-Pro with 262k context and reasoning, tool use, function calling, and multimodal inputs.