GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
nex-agi
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
nex-agi
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Model weights for the Nex-N2.5 family will be released as open source, alongside hosted online services.
We welcome developers and enterprises to integrate and try Nex-N2.5 and share their feedback.
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.1, 2 Bold marks the best result in each benchmark, including ties; — indicates unavailable data.10
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.
bash
# 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_coderSingle node with 8 × H100:
bash
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_bufferSingle node with 2 × H100:
bash
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_bufferFor the best generation quality, we recommend the following sampling parameters:
temperature: 0.7top_p: 0.95top_k: 40Use reasoning_effort to control the thinking behavior of Nex-N2.5:
reasoning_effort | Mode | Behavior |
|---|---|---|
"none" | Non-thinking | Respond directly without a reasoning trace. |
"medium" (default) | Adaptive thinking | Let the model decide whether and how much to think before responding. |
"high" | Thinking | Always enable thinking before responding. |
For adaptive thinking, set reasoning_effort to "medium" in your OpenAI-compatible Chat Completions request. Replace <served-model-name> with the model name exposed by your server:
json
{ "model": "<served-model-name>", "messages": [ {"role": "user", "content": "Explain how binary search works."} ], "reasoning_effort": "medium"}The chat template uses reasoning_effort; parameters such as enable_thinking and thinking_mode require gateway-specific translation.
Nex-series models support robust function-calling capabilities. To enable function calling, add the --tool-call-parser qwen3_coder flag when launching the server:
bash
python -m sglang.launch_server --model-path /path/to/your/model --tool-call-parser qwen3_coderWhen the model produces a reasoning trace, configure SGLang to separate it from the final response:
--reasoning-parser qwen3--reasoning-parser deepseek-r1The deployment commands above include the appropriate reasoning parser and --tool-call-parser qwen3_coder. The parser extracts reasoning content; use reasoning_effort to select the thinking mode.
# 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_coderdocker 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_bufferdocker 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_bufferpython -m sglang.launch_server --model-path /path/to/your/model --tool-call-parser qwen3_coder{ "model": "<served-model-name>", "messages": [ {"role": "user", "content": "Explain how binary search works."} ], "reasoning_effort": "medium"}