Sugar Glider 120B

Sugar Glider (i14-sugarglider-nemotron3-super-120B-v1) is a thinking model served on the i14 API. It thinks before it answers. Your request gets the reasoning in reasoning_content and the answer in content. It accepts text input.

Model Details

Field	Value
Model ID	`i14-sugarglider-nemotron3-super-120B-v1`
Input	Text only. The model does not support images.
Owner	i14

Use via the API

Send a request to the i14 endpoint and set model to i14-sugarglider-nemotron3-super-120B-v1.

Sugar Glider thinks before it answers, and thinking tokens count toward max_tokens. Set max_tokens high enough for both the thinking and the answer. If it is too low, content comes back empty and finish_reason is length.

curl https://api.i14.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $I14_API_KEY" \
  -d '{
    "model": "i14-sugarglider-nemotron3-super-120B-v1",
    "messages": [
      {
        "role": "user",
        "content": "Write a Python function that reverses a string."
      }
    ],
    "max_tokens": 8192,
    "stream": true
  }'

Use via OpenAI SDK

Sugar Glider works with the OpenAI SDK. Point the SDK’s base_url at the i14 endpoint, pass your API key, and set the model to i14-sugarglider-nemotron3-super-120B-v1.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.i14.ai/v1",
    api_key=os.environ["I14_API_KEY"],
)

stream = client.chat.completions.create(
    model="i14-sugarglider-nemotron3-super-120B-v1",
    messages=[
        {
            "role": "user",
            "content": (
                "Write a Python function that reverses a string."
            ),
        }
    ],
    max_tokens=8192,
    stream=True,
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")