Nex N2.5 Pro
8430°
Run this model
Offers / Ads
Nex AGI | 262,144 token context | $0.07/M input, $0.25/M output. Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file changes, run commands, launch applications, interact with browser and desktop interfaces, and test software from the user's perspective. When observed behavior does not match the intended result, Nex-N2.5 can diagnose the issue, revise its implementation, and test again. This makes it especially effective for autonomous software engineering, GUI-based QA, computer-use automation, deep research, and scientific workflows where success must be demonstrated in the environment—not merely inferred from generated code.
Guides for this model
Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs
How much VRAM do I actually need for local AI?
Open weights vs open source vs API-only: what you are actually allowed to do
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
Nex-N2.5-Pro is an open-weights agentic model from Nex AGI designed to complete long-horizon tasks in real environments, not just generate plausible output. Its defining trait is a visual feedback loop: it acts, observes the screen, diagnoses failures, and retries until the result is demonstrably correct. If you need a model that can drive a browser, test a GUI, or autonomously work through a multi-file codebase, this is built for that.
Known for
- Agentic coding with multi-file edits, command execution, and self-correction.
- Computer-use and browser automation grounded in live visual feedback.
- 262,144-token context window for long codebases and research sessions.
- Open weights available on Hugging Face for self-hosted deployment.
- Part of a three-tier family; Pro sits between mini and the trillion-parameter Max.
Watch out for
- Weights are open but check the licence terms on Hugging Face before commercial use.
- Running a model this capable locally will demand serious VRAM; hosted access is via OpenRouter.
- Vision and agentic loops add latency; not the right pick for simple, fast completions.
Prompts to try
Autonomous bug fix loop
You have access to a terminal and browser. Clone the repository at https://github.com/example/sample-app, run the test suite, identify the first failing test, trace it to its root cause across files, implement a fix, and run the tests again to confirm the failure is resolved. Show each step and what you observed.
GUI QA from screenshot
I'm attaching a screenshot of a web app's checkout flow. Identify any UI elements that appear broken, misaligned, or inconsistent with standard e-commerce conventions. For each issue, describe what you see, why it is a problem, and suggest a specific fix a developer could implement today.
Deep research synthesis
Search the web for the current state of research on solid-state battery electrolytes. Identify the three most-cited technical barriers to commercialization, find at least two recent papers or announcements addressing each barrier, and produce a structured summary with your assessment of which barrier is closest to being solved and why.
Compare with
- Nex-N2.5-MiniOpen-weights model262,144 token context · $0.02/M input, $0.10/M output
- GPT-6 LunaAPI-only model1,050,000 token context · $0.10/M input, $0.50/M output
- GPT-5.6 LunaAPI-only model1,050,000 token context · $0.20/M input, $1.20/M output
- Claude Opus 5.5API-only model1,000,000 token context · $4.00/M input, $20.00/M output
More text models from nex-agi
Questions people ask
- Are the weights open and can I run Nex-N2.5-Pro locally?
- Yes, weights are released as open source on Hugging Face under the nex-agi/Nex-N2.5-Pro repository. Running it locally is possible, though the model's agentic and vision capabilities mean you will want substantial hardware.
- What does Nex-N2.5-Pro cost and what is the context window?
- Via the hosted API on OpenRouter it is priced at $0.07 per million input tokens and $0.25 per million output tokens, with a 262,144-token context window.
- How does Nex-N2.5-Pro differ from Nex-N2.5-Max and Nex-N2.5-mini?
- Pro is the mid-tier option: it shares the multimodal, computer-use foundations with mini, while Max is a separate text-only build on a 1.6-trillion-parameter Mixture-of-Experts architecture trained at trillion-parameter scale for the first time.
Captain's verdictA serious agentic coding and computer-use model that earns its place by closing the loop between action and verified outcome, not just generating code and hoping.
Model card on Hugging Face
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
Also ranked: #59 Hottest Text / LLM model · #59 Hottest Text / LLM text model
Not this creator?
Get your own badge
Nex N2.5 Pro Popularity Trend
Heat score since 8 Sep 2026
Heat score
8,430°
This week
▲
18.3%
8,408° then, 8,430° now
This month
▲
209%
8,282° then, 8,430° now
Past year
n/a
Wasn't released/tracked
7,000°
Floor
The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.
+1,430°
OpenRouter tokens
584,908,336,734 tokens this model processed through OpenRouter in the last 30 days, prompts and answers together. Every 10,000,000 tokens count as one download in the download term, 58,490 in all; the last day's tokens join the adoption rate. Source: OpenRouter (openrouter.ai/rankings).
Show detailed breakdown
Every number on this site can be checked. This model's heat score is 8,430°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.
- 1Start at the floor.Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.7,000°running total
- 2Add the downloads.58,490 download-equivalents in all, from OpenRouter tokens. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.+1,430°8,430°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.8,430°
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.
Nex N2.5 Pro is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153