Gpt-oss-20b

pip install requests

export OVH_AI_ENDPOINTS_ACCESS_TOKEN=<your-access-token>

import os
import requests
 
# You can use the model dedicated URL
url = "https://gpt-oss-20b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions"
# Or our unified endpoint for easy model switching with optimal OpenAI compatibility
url = "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions"
payload = {
    "max_tokens": 512,
    "messages": [
        {
            "content": "Explain gravity to a 6 years old",
            "role": "user"
        }
    ],
    "model": "gpt-oss-20b",
    "temperature": 0,
}
 
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.getenv('OVH_AI_ENDPOINTS_ACCESS_TOKEN')}",
}
 
response = requests.post(url, json=payload, headers=headers)
if response.status_code == 200:
    # Handle response
    response_data = response.json()
    # Parse JSON response
    choices = response_data["choices"]
    for choice in choices:
        text = choice["message"]["content"]
        # Process text and finish_reason
        print(text)
        reasoning_text = choice["message"]["reasoning_content"]
        # Process reasoning_content
        print(reasoning_text)
else:
    print("Error:", response.status_code, response.text)

pip install openai

export OVH_AI_ENDPOINTS_ACCESS_TOKEN=<your-access-token>

import os

from openai import OpenAI

# You can use the model dedicated URL
url = "https://gpt-oss-20b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1"
# Or our unified endpoint for easy model switching with optimal OpenAI compatibility
url = "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1

client = OpenAI(
    base_url=url,
    api_key=os.getenv("OVH_AI_ENDPOINTS_ACCESS_TOKEN")
)

def chat_completion(new_message: str) -> str:
    history_openai_format = [{"role": "user", "content": new_message}]

    choice = client.chat.completions.create(
        model="gpt-oss-20b",
        messages=history_openai_format,
        temperature=0,
        max_tokens=1024,
        reasoning_effort="low", # Either low, medium, or high
    ).choices.pop()
    
    print(f"** REASONING ** \n {choice.message.reasoning_content}\n")
    print(f"** CONTENT ** \n {choice.message.content}")

if __name__ == '__main__':
    chat_completion("Explain gravity for a 6 years old")