Nex-N2-Mini
Nex AGI · released Jun 4, 2026 · nex-agi/Nex-N2-Mini
- Type
- Open weightsApache License 2.0
- Params
- 35.1B
- Context
- 262K
active per word not recorded by us · about 197K words of context
Our take
Written Sep 2, 2026Nex-N2-Mini is a 35.1-billion-parameter vision-language model released in June 2026 with a permissive Apache licence. It accepts text and images and can handle up to 262,144 tokens in a single request, though no benchmark scores are available to verify its quality.
Pick this for Apache-licensed multimodal deployment where permissive terms matter, or for very low-cost vision-language inference. Use it for long-context document and image workflows up to 262K tokens. Skip it if you need measured quality data, or if you want to compare active parameter counts or throughput across providers.
The case for it
- Apache 2.0 licence allows commercial use, fine-tuning and redistribution.
- Extremely low cost for a multimodal model of this scale, with the same rate across all three tracked offers.
- 262,144-token request limit is large for its parameter class.
The case against it
- No benchmark scores in our data — chat, coding, reasoning and vision performance are all unverified.
- Active parameter count is undisclosed, so MoE efficiency and per-token compute cost cannot be assessed.
- Throughput is only measured on the vendor's own endpoint; the third-party figure is unverified.
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
Loads, but do not expect an assistant. Some of the weights sit in ordinary system memory, which is far slower than the card.22.1 GB of weights, plus 2 GB for the software that runs it and the smallest conversation it can hold, comes to 24.1 GB against the 22.8 GB this 24 GB device leaves free.
Comfortable fit
GeForce RTX 5090 · 32 GB
Room to spare. 6.6 GB spare means a 10% error in the size would not change the answer.
Apple M3 Pro (18-core GPU) · 36 GB
Room to spare. 2.8 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 between 23 days and 52 days ago — each listing carries its own date.
- per 1M tokens
- $0.025 in / $0.10 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 | $0.025 / $0.10checked 24 days ago | 262K | not measured | Unknown | Unknown | Unknown |
| Nex AGIThrough OpenRouter | $0.025 / $0.10checked 23 days ago | 262K | not measured | No | Yes30 days | Unknown |
| Nex AGIfp8Through OpenRouter | $0.025 / $0.10checked 52 days ago | 262K | not measured | No | Yes30 days | Unknown |
OpenRouterAcross the 3 listings we hold: 2 say they do 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 AGIThrough OpenRouter | ✓ | ✓ | ✓ |
| Nex AGIfp8Through OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
Models people weigh against Nex-N2-Mini
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 3 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-Mini
- Architecture
- Mixture of experts
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- nex-agi-nex-n2-mini