Instructions to use nex-agi/Nex-N2.5-Pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nex-agi/Nex-N2.5-Pro with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="nex-agi/Nex-N2.5-Pro")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("nex-agi/Nex-N2.5-Pro")
model = AutoModelForMultimodalLM.from_pretrained("nex-agi/Nex-N2.5-Pro", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nex-agi/Nex-N2.5-Pro with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nex-agi/Nex-N2.5-Pro"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nex-agi/Nex-N2.5-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nex-agi/Nex-N2.5-Pro

SGLang

How to use nex-agi/Nex-N2.5-Pro with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "nex-agi/Nex-N2.5-Pro" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nex-agi/Nex-N2.5-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "nex-agi/Nex-N2.5-Pro" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nex-agi/Nex-N2.5-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nex-agi/Nex-N2.5-Pro with Docker Model Runner:
```
docker model run hf.co/nex-agi/Nex-N2.5-Pro
```

Nex-N2.5-Pro / README.md

00index

Model card: sync github.com/nex-agi/Nex-N2.5 @ 0e5ba9c (HF collection link, Thinking Control section)

aa66e19 verified 12 days ago

14.1 kB

license: apache-2.0
pipeline_tag: text-generation
library_name: transformers

💻 GitHub · 🤗 Hugging Face · 🌐 Website · 🔀 OpenRouter (Pro)

🚧 Nex-N2.5-Pro weights are coming soon.

Nex-N2.5

A next-generation family of agentic models built for long-horizon tasks in real-world environments.

Today, Nex-AGI officially introduces Nex-N2.5, its next-generation family of agentic models.

Nex-N2.5 is available in three sizes: mini, Pro, and Max. Nex-N2.5-mini and Nex-N2.5-Pro continue to build on the multimodal foundations of Nex-N2, with focused improvements in computer use, web browsing, and visually grounded agentic capabilities. Nex-N2.5-Max is built on a 1.6-trillion-parameter, text-only Mixture-of-Experts (MoE) foundation model, marking our first complete post-training effort at trillion-parameter scale.

For long-horizon tasks in real-world environments, Nex-N2.5 further strengthens its ability to act continuously and self-correct through visual feedback. The models can operate computers and browsers, as well as autonomously execute and test programs. Vision is therefore no longer merely an input modality; it has become a critical interface through which an agent perceives its environment, verifies outcomes, and moves a task forward.

Building on this foundation, we have further expanded the range of agent training environments, task types, and productivity scenarios, while completing systematic post-training at trillion-parameter scale for the first time. Through broader task coverage and richer environmental feedback, Nex-N2.5 delivers further gains in scientific research, knowledge work, and complex productivity tasks. This work also provides valuable practical experience for training agentic capabilities in even larger models.

By jointly advancing model training, infrastructure, and real-world agent scenarios, Nex-AGI aims to continue driving progress in agentic intelligence.

Open Source

Model weights for the Nex-N2.5 family will be released as open source, alongside hosted online services.

Nex-N2.5-Max: Hugging Face | ModelScope
Nex-N2.5-Pro: Hugging Face | ModelScope
Nex-N2.5-mini: Hugging Face | ModelScope
Hosted Access: OpenRouter (Nex-N2.5-Pro)
Websites: Global

We welcome developers and enterprises to integrate and try Nex-N2.5 and share their feedback.

Performance

We evaluate Nex-N2.5 across coding, agentic workflows, computer use, and multimodal understanding.

The tables below compare Nex-N2.5-mini, Nex-N2.5-Pro, and Nex-N2.5-Max with leading models across our evaluation suite. Bold marks the best result in each benchmark, including ties; — indicates unavailable data.

Text Benchmarks

Benchmark	Nex-N2.5-mini	Nex-N2.5-Pro	Nex-N2.5-Max	Claude Opus 5	GPT-5.6 Sol	Kimi-K3	GLM-5.3	DeepSeek-V4-Pro	Qwen3.8-Max
CODING
Terminal-Bench 2.1	73.4	82.7	86.1	89.1	88.8	88.3	88.2	87.9	86.6
SWE-Bench Pro	43.8	61.2	65.7	79.2	64.6	63.3	64.6	55.4	67.7
DeepSWE v1.1	36.1	55.8	65.6	73.7	72.7	67.5	66.9	62.8	69.3
AGENTIC
AutomationBench v1.0.6	32.3	44.2	50.2	50.3	45.8	46.7	48.2	43.2	50.8
Toolathlon Verified	54.6	68.5	74.7	76.5	74.9	76.5	73.0	74.1	73.3
GDPval-AA v2	1446	1628	1713	1861	1748	1668	1769	1554	1630
Job Bench	28.5	41.4	53.6	65.7	45.4	52.9	58.2	54.1	64.0
BrowseComp	83.4	89.7	92.6	90.8	90.4	91.2	—	—	—

Multimodal Benchmarks

Benchmark	Nex-N2.5-mini	Nex-N2.5-Pro	MiniMax-M3	Claude Opus 5	GPT-5.6 Sol	Kimi-K3	GLM-5.3-Flash	DeepSeek-V4-Flash-Vision	Qwen3.8-Max
OSWorld-Verified	71.2	82.2	75.2	83.4	83.2	84.8	62.3	76.7	86.1
OSWorld-2	30.5	56.4	22.3	68.3	62.7	58.3	—	—	46.7
WebTest	48.6	52.8	—	—	54.0	—	—	—	52.3
WebArena-Verified	63.4	67.6	—	—	69.7	71.6	—	62.3	66.8
OSWorld-G	82.9	87.4	—	76.8	77.7	79.6	83.3	59.4	84.9
Vision2Web	52.9	68.2	59.0	—	79.8	—	—	—	75.1
SWE-MM	25.5	38.2	—	59.4	40.2	37.3	20.6	39.2	39.2
OmniDoc	89.7	92.2	91.6	—	92.9	91.1	—	—	92.1

Usage

Docker Deployment

We also provide a prebuilt Docker image with our customized sglang fork preinstalled: nexagi/sglang:v0.5.18-nex-patch. The launch command is the same as above.

Nex-N2.5-Max

# Multi-node (2 nodes, 16 x H200). Run the same command on every node with:
#   <node-rank> = 0 on the head node, 1 on the other node
#   <node0-ip>  = IP of the head node (reachable from all others)
docker run --gpus all --shm-size 32g --network host \
  -v /path/to/your/model:/model \
  nexagi/sglang:v0.5.18-nex-patch \
  python3 -m sglang.launch_server \
    --model-path /path/to/your/model \
    --trust-remote-code \
    --host 0.0.0.0 \
    --port 8000 \
    --nnodes 2 \
    --node-rank "${NODE_RANK}" \
    --dist-init-addr "${MASTER_ADDR}:5000" \
    --tp 16 \
    --pp-size 1 \
    --dp 1 \
    --ep-size 16 \
    --attention-backend dsv4 \
    --kv-cache-dtype fp8_e4m3 \
    --page-size 256 \
    --moe-a2a-backend deepep \
    --moe-runner-backend deep_gemm \
    --moe-dense-tp-size 1 \
    --deepep-mode auto \
    --context-length 262144 \
    --mem-fraction-static 0.84 \
    --chunked-prefill-size 8192 \
    --enable-mixed-chunk \
    --disable-overlap-schedule \
    --max-running-requests 64 \
    --cuda-graph-max-bs-decode 64 \
    --cuda-graph-backend-decode full \
    --cuda-graph-backend-prefill disabled \
    --chat-template /path/to/nex-n2.5-max/chat_template.jinja \
    --reasoning-parser deepseek-r1 \
    --tool-call-parser qwen3_coder

Nex-N2.5-Pro

Single node with 8 × H100:

docker run --gpus all --shm-size 32g --ipc=host \
  -p 30000:30000 \
  -v /path/to/your/model:/model \
  nexagi/sglang:v0.5.18-nex-patch \
  python3 -m sglang.launch_server \
    --model-path /model \
    --tp 8 \
    --host 0.0.0.0 --port 30000 \
    --reasoning-parser qwen3 \
    --tool-call-parser qwen3_coder \
    --chat-template /path/to/nex-N2.5-Pro/chat-template.jinja \
    --mamba-scheduler-strategy extra_buffer

Nex-N2.5-mini

Single node with 2 × H100:

docker run --gpus all --shm-size 32g --ipc=host \
  -p 30000:30000 \
  -v /path/to/your/model:/model \
  nexagi/sglang:v0.5.18-nex-patch \
  python3 -m sglang.launch_server \
    --model-path /model \
    --tp 2 \
    --host 0.0.0.0 --port 30000 \
    --reasoning-parser qwen3 \
    --tool-call-parser qwen3_coder \
    --chat-template /path/to/nex-N2.5-mini/chat-template.jinja \
    --mamba-scheduler-strategy extra_buffer

Recommended Sampling Parameters

For the best generation quality, we recommend the following sampling parameters:

temperature: 0.7
top_p: 0.95
top_k: 40

Function Calling

Nex-series models support robust function-calling capabilities. To enable function calling, add the --tool-call-parser qwen3_coder flag when launching the server:

python -m sglang.launch_server --model-path /path/to/your/model --tool-call-parser qwen3_coder

Reasoning Parser

Nex-series models emit explicit reasoning traces. Add the --reasoning-parser qwen3 flag to parse the reasoning content separately from the final response. It can be combined with the function-calling parser above:

python -m sglang.launch_server --model-path /path/to/your/model --tool-call-parser qwen3_coder --reasoning-parser qwen3

Thinking Control

Nex-N2.5 models support three thinking modes, selected per request with the OpenAI-compatible reasoning_effort field:

`reasoning_effort`	Mode	Behavior
`"none"`	Thinking off	The model answers directly, without a reasoning trace.
`"medium"` (default)	Adaptive thinking	The model decides per request whether, and how much, to reason.
`"high"`	Thinking on	The model always produces a full reasoning trace before answering.

curl http://localhost:30000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nex-agi/Nex-N2.5-Pro",
    "messages": [{"role": "user", "content": "How many prime numbers are there below 100?"}],
    "reasoning_effort": "high"
  }'