Open agentic MoE model (397B total, 17B active) for coding, tool use, and research workflows
- Context
- 262K
- Released
- 4mo ago
- Parameters
- —
Sources:models.dev
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Nex Agi
- Model family
- —
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- June 2, 2026
- Model ID
nex-agi/nex-n2-pro- Openness
- Open weights
- License
- —
- Parameters
- —
- Input modalities
- text, image
- Output modalities
- text
- Modality
- text+image->text
- Max output tokens
- 262K
- Hugging Face
- —
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- nex-agi/nex-n2-pro
- Last updated
- 2026-06-02
- Model context
- 262K
- Model output limit
- 262K
- Open weights
- Yes
- File attachments
- Yes
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Temperature control
- Yes
Downloadable weights
Complete source record (JSON)
{
"id": "nex-agi/nex-n2-pro",
"name": "Nex-N2-Pro",
"description": "Open agentic MoE model (397B total, 17B active) for coding, tool use, and research workflows",
"last_updated": "2026-06-02",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"temperature": true,
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"release_date": "2026-06-02",
"open_weights": true,
"weights": [
{
"label": "Hugging Face",
"url": "https://huggingface.co/nex-agi/Nex-N2-Pro"
}
]
}Infrastructure
Provider availability
Provider endpoint data will appear after this model's first OpenRouter endpoint sync.
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.