Skip to main content
Accelerate your development with our API within a minute.
Qubrid AI simplifies the process of integrating high-performance open-source models, allowing you to run inference with just a few lines of code.

​
1. Register for an account

Begin by creating an account to obtain your unique API key. Once your account is active, configure your environment by exporting your key as a variable named QUBRID_API_KEY:
Shell
export QUBRID_API_KEY=xxxxx

​
2. Run your first Model Inference

Select the model you wish to run. For this demonstration, we will utilize OPENAI GPT OSS 120B with streaming enabled to show real-time token generation. 
import requests
import json
from pprint import pprint

url = "https://platform.qubrid.com/api/v1/qubridai/chat/completions"
headers = {
"Authorization": "Bearer <QUBRID_API_KEY>",
"Content-Type": "application/json"
}

data = {
"model": "openai/gpt-oss-120b",
"messages": [
{
  "role": "user",
  "content": "Explain quantum computing to a 5 year old."
}
],
"temperature": 0.7,
"max_tokens": 4096,
"stream": False,
"top_p": 0.8
}

response = requests.post(
  url,
  headers=headers,
  json=data, 
)
content_type = response.headers.get("Content-Type", "")

if "application/json" in content_type:
  pprint(response.json())

else:
  for line in response.iter_lines(decode_unicode=True):
      if not line:
          continue

      if line.startswith("data:"):
          payload = line.replace("data:", "").strip()

          if payload == "[DONE]":
              break

          try:
              chunk = json.loads(payload)
              pprint(chunk)
          except json.JSONDecodeError:
              print("Raw chunk:", payload)
Congratulations! You have successfully run your first inference request to the Qubrid AI cloud.

​
Next steps