Nex-N2.5-Pro
Nex AGI · released Sep 8, 2026 · nex-agi/Nex-N2.5-Pro
- Type
- Open weightsApache License 2.0
- Params
- 397B
- Context
- 262K
active per word not recorded by us · about 197K words of context
Our take
Written Sep 30, 2026Nex-N2.5-Pro is a model you can download and run yourself, with a licence that allows commercial use, changes and redistribution. Nothing here measures how good its answers are, so the decision rests on its long request capacity, its size and what the hosts charge.
Use it for long-document work or questions that arrive with an image attached, where the bill matters and you can judge the output yourself. You can also download it and run it yourself, and the licence allows commercial use, changes and redistribution (Apache License 2.0). Skip it if you need measured evidence of coding, reasoning or chat quality before committing, or if you need a model that fits on a workstation.
The case for it
- The licence allows commercial use, changes and redistribution, so building a product on it is permitted.
- A request capacity of 262144 tokens means long documents need not be split up first, though whether it reliably uses all of that room is unverified in our data.
- Text and images go into the same request, so a screenshot or diagram does not have to be described in words first.
The case against it
- No benchmark scores are supplied, so nothing here says how well it codes, reasons or chats; it needs a trial on work you can check yourself.
- At 396.8 billion parameters, with no figure for how many work on any one token, the memory it needs in use is unverified in our data.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 124.9 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.075 in / $0.25 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.075 / $0.25checked 4 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
| Nex AGIfp8Through OpenRouter | $0.075 / $0.25checked 4 hours ago | 262K236K max reply | 17 tok/s | No | Yes30 days | Unknown |
Across the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✗ | ✓ |
| Nex AGIfp8Through OpenRouter | ✓ | ✗ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 2 of 2 listings say yes.
Models people weigh against Nex-N2.5-Pro
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- We do not hold the active parameter count for it, so how much of it runs on any one token is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- nex-agi/Nex-N2.5-Pro
- Architecture
- Mixture of experts
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- nex-agi-nex-n2-5-pro