LLM Reference

Nex-N2-Pro

Released
2026-06-02
Last refreshed
2026-06-08
Status
Researched today
Open SourceCommercial use allowedMultimodalCodingRAGAgentsLong contextVisionJSON / Tool use

Nex-N2-Pro is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 262k context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
Nex-N2
Released
2026-06-02
Context
262k
Parameters
397B total, 17B active (MoE)
Architecture
Mixture of Experts
Specialization
coding
Openness
Open source
License
Apache 2.0(OSI)Commercial use allowed
Training
pretrained
Created by

Open agentic AI with Agentic Thinking

Website
Pricing
Output / 1M
-
Input / 1M
-

Cheapest of 1 route · SiliconFlow

About

Open-source agentic model from Nex AGI, built on Qwen3.5-397B-A17B (397B total, 17B active MoE). Features Agentic Thinking, an adaptive reasoning approach that adjusts depth per step. Designed for complex coding, long-horizon task execution, and deep research.

Nex-N2-Pro is an open-source model in the Nex-N2 family. The structured metadata tracks a 262k-token context window, multimodal input, reasoning, function calling, and tool use. This page tracks provider routes through SiliconFlow. Headline tracked benchmarks include SWE-bench Pro 58.8 and BrowseComp 83.7.

Top use-case fit: coding, agents, and build tasks

Coding

1 relevant benchmark in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
SiliconFlow--
ServerlessPartial

Capabilities

VisionMultimodalReasoningFunction CallingTool Use

Benchmark peer barsfor Coding

Benchmark scores(2)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
SWE-bench Pro58.8SWE-bench Pro — self-reportedhttps://huggingface.co/nex-agi/Nex-N2-Pro
BrowseComp83.7BrowseComp — self-reportedhttps://huggingface.co/nex-agi/Nex-N2-Pro

Migration checks

No linked migration route is available for this model yet.