Nex-N2-Pro
Nex AGI · released Jun 3, 2026 · nex-agi/Nex-N2-Pro
- Type
- Open weightsApache License 2.0
- Params
- 397B
- Context
- 262K
about 197K words of context
Our take
Written Aug 2, 2026Nex-N2-Pro is a large downloadable model from Nex AGI that accepts text and images and returns text, released in 2026 with a permissive Apache licence. Its context limit reaches 262,144 tokens, though no benchmark scores are available to confirm its quality.
Pick this for open weights at around 397 billion parameters with a fully permissive licence. Use it for long-document work or hosted inference where the primary tier suits your budget. Skip it if you need verified quality scores or the fastest option without a steep throughput premium.
The case for it
- Fully open weights under Apache License 2.0, allowing commercial use, fine-tuning and redistribution.
- 262,144-token context limit for long-document workloads.
- Higher throughput available on a secondary host at 86.5 tokens per second, versus 65 on the primary host.
The case against it
- No measured quality scores in our data — no Elo, MMLU or other benchmarks are listed.
- The fastest host charges twice the input rate and two-and-a-half times the output rate of the primary tier.
- Whether this is a mixture-of-experts design, and how many parameters are active per token, is undisclosed.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Nex-N2-Pro — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 3 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.25 in / $1.00 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.25 / $1.00 | 262K | not measured | Unknown | Unknown | Unknown |
| Nex AGIfp8 | $0.25 / $1.00 | 262K | 63 tok/s | No | Yes30 days | Unknown |
| SiliconFlow | $0.50 / $2.50 | 262K | 109 tok/s | No | No | Confirmed |
Across the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✗ | ✗ |
| Nex AGIfp8 | ✓ | ✗ | ✗ |
| SiliconFlow | ✓ | ✗ | ✗ |
Tool calling: 3 of 3 listings say yes. JSON output: 0 of 3 listings say yes, 3 say no. Strict schema: 0 of 3 listings say yes, 3 say no.
When we formed this view
Dates behind this page
Prices last checked 4d ago
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 board we watch has turned up a score, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings do not say whether they train on prompts.
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-Pro
- Architecture
- Mixture of experts
- Modality record
- text+image->text
- Catalogue slug
- nex-agi-nex-n2-pro