N
Nex-N2-ProOPEN
Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total.
Prices update automatically — checked daily against provider list prices.
- $0.44 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 43% of the 191 open-weight models tracked here
Benchmarks & performance
Independent benchmark scores for Nex-N2-Pro, measured by Artificial Analysis. Higher is better.
For the same budget, Nex-N2-Pro delivers 6.6 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $1.35 per 1M tokens (median of 18) — this one costs $0.44.
Cheaper and better on this index: GLM 5.3 Flash · Gemini 3.7 Flash (batch) · GPT-5.6 Luna (batch) and 3 more
About this model
Nex-N2-Pro is an open-weight AI model by Nex agi. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Nex-N2-Pro?
Nex-N2-Pro is an AI language model from Nex agi. It is open-weight: you can download it and run it on your own hardware, for free. It scores 41.7 on the Artificial Analysis intelligence index.
Is Nex-N2-Pro free?
The weights are free and open — you can self-host Nex-N2-Pro and pay nothing per token. If you prefer a hosted API, list prices are $0.25 per million input tokens and $1 per million output tokens.
What is Nex-N2-Pro good at?
Independent benchmarks from Artificial Analysis give it GPQA 89.2%, Humanity's Last Exam 33.7%, Long Context Reasoning 76.3%, SciCode 41.8%, IFBench 66.2%, τ²-Bench 81.6%, τ-Bench Banking 17.5%, Terminal-Bench 67.8%. It is particularly used for code generation.
How fast is Nex-N2-Pro?
It generates about 138.7 tokens per second, with a median 0.88s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Nex-N2-Pro?
Yes. Nex-N2-Pro has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.