%%capture

!pip install -q openai aisuite  docstring-parser  python-dotenv

import os, sys

## Recommended way of getting configuration
if os.getenv("COLAB_RELEASE_TAG"):
   print("Running in Colab")
   from google.colab import userdata
   NEBIUS_API_KEY = userdata.get('NEBIUS_API_KEY')
else:
   print("NOT running in Colab")
   from dotenv import load_dotenv
   this_dir = os.path.abspath('')
   parent_dir = os.path.dirname(this_dir)
   sys.path.append (os.path.abspath (parent_dir))
   load_dotenv()
   NEBIUS_API_KEY = os.getenv('NEBIUS_API_KEY')

## quick hack (not recommended) - you can hardcode the config key here
# NEBIUS_API_KEY = "your_key_here"

if NEBIUS_API_KEY:
  print ('✅ NEBIUS_API_KEY found')
  os.environ['NEBIUS_API_KEY'] = NEBIUS_API_KEY
else:
  raise RuntimeError ('❌ NEBIUS_API_KEY NOT found')

NOT running in Colab
✅ NEBIUS_API_KEY found

%%time

import os
import aisuite as ai

client = ai.Client()

provider = "nebius"
model_id = "openai/gpt-oss-20b-Instruct-2507"

messages = [
    {
        "role": "system",
        "content": "You are a helpful assistant."
    },
    {
        "role": "user",
        "content": "What is the capital of France?"
    },
]

response = client.chat.completions.create(
    model=f"{provider}:{model_id}",
    messages=messages,
)

print ('----model answer -----')
print (response.choices[0].message.content)
print ('\n----- full response ----')
print(response.to_json())
print ('---------')

----model answer -----
The capital of France is Paris.

----- full response ----
{
  "id": "chatcmpl-ee7a8e79ac83447686508087cde32c70",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "The capital of France is Paris.",
        "refusal": null,
        "role": "assistant",
        "annotations": null,
        "audio": null,
        "function_call": null,
        "tool_calls": [],
        "reasoning_content": null
      },
      "stop_reason": null,
      "token_ids": null
    }
  ],
  "created": 1762231897,
  "model": "openai/gpt-oss-20b-Instruct-2507",
  "object": "chat.completion",
  "service_tier": null,
  "system_fingerprint": null,
  "usage": {
    "completion_tokens": 8,
    "prompt_tokens": 26,
    "total_tokens": 34,
    "completion_tokens_details": null,
    "prompt_tokens_details": null
  },
  "prompt_logprobs": null,
  "prompt_token_ids": null,
  "kv_transfer_params": null
}
---------
CPU times: user 752 ms, sys: 310 ms, total: 1.06 s
Wall time: 5.64 s

Run models on Nebius Token Factory (via aisuite API)¶

References and Acknowledgements¶

Pre requisites¶

1 - Install Dependencies¶

2 - Load Configuration¶

3 - Pick a Model¶

4 - Run the Model¶

5 - Try Your Queries¶