Chat Completion (LLM)

Basic Usage

import os
from huggingface_hub import InferenceClient

client = InferenceClient(
    provider="cerebras",
    api_key=os.environ["HF_TOKEN"],
)

completion = client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[
        {
            "role": "user",
            "content": "What is the capital of France?"
        }
    ],
)

print(completion.choices[0].message)

cURL Example

curl https://router.huggingface.co/v1/chat/completions \
    -H "Authorization: Bearer $HF_TOKEN" \
    -H 'Content-Type: application/json' \
    -d '{
        "messages": [
            {
                "role": "user",
                "content": "What is the capital of France?"
            }
        ],
        "model": "openai/gpt-oss-120b:cerebras",
        "stream": false
    }'

Using HF-Inferoxy Token Management

from huggingface_hub import InferenceClient
from huggingface_hub.errors import HfHubHTTPError
from hf_token_utils import get_proxy_token, report_token_status

def cerebras_chat_completion(proxy_api_key: str):
    # Get token from proxy server (requires authentication)
    token, token_id = get_proxy_token(api_key=proxy_api_key)
    
    # Create client with managed token
    client = InferenceClient(
        provider="cerebras",
        api_key=token
    )
    
    try:
        # Make chat completion request
        completion = client.chat.completions.create(
            model="openai/gpt-oss-120b",
            messages=[
                {
                    "role": "user",
                    "content": "What is the capital of France?"
                }
            ],
        )
        
        # Report success
        report_token_status(token_id, "success", api_key=proxy_api_key)
        
        print(completion.choices[0].message)
        return completion
        
    except HfHubHTTPError as e:
        # Report the error
        report_token_status(token_id, "error", str(e), api_key=proxy_api_key)
        raise
    except Exception as e:
        # Report generic error
        report_token_status(token_id, "error", str(e), api_key=proxy_api_key)
        raise

# Usage
if __name__ == "__main__":
    # You need to get your API key from the admin or create a user account
    # See RBAC_README.md for details on user management
    proxy_api_key = "your_proxy_api_key_here"  # Get this from admin
    cerebras_chat_completion(proxy_api_key)

Chat Completion (VLM)

Basic Usage

import os
from huggingface_hub import InferenceClient

client = InferenceClient(
    provider="cerebras",
    api_key=os.environ["HF_TOKEN"],
)

completion = client.chat.completions.create(
    model="meta-llama/Llama-4-Scout-17B-16E-Instruct",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Describe this image in one sentence."
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
                    }
                }
            ]
        }
    ],
)

print(completion.choices[0].message)

cURL Example

curl https://router.huggingface.co/v1/chat/completions \
    -H "Authorization: Bearer $HF_TOKEN" \
    -H 'Content-Type: application/json' \
    -d '{
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": "Describe this image in one sentence."
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
                        }
                    }
                ]
            }
        ],
        "model": "meta-llama/Llama-4-Scout-17B-16E-Instruct:cerebras",
        "stream": false
    }'

Using HF-Inferoxy Token Management

from huggingface_hub import InferenceClient
from huggingface_hub.errors import HfHubHTTPError
from hf_token_utils import get_proxy_token, report_token_status

def cerebras_vlm_completion(proxy_api_key: str):
    # Get token from proxy server (requires authentication)
    token, token_id = get_proxy_token(api_key=proxy_api_key)
    
    # Create client with managed token
    client = InferenceClient(
        provider="cerebras",
        api_key=token
    )
    
    try:
        # Make VLM completion request
        completion = client.chat.completions.create(
            model="meta-llama/Llama-4-Scout-17B-16E-Instruct",
            messages=[
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "text",
                            "text": "Describe this image in one sentence."
                        },
                        {
                            "type": "image_url",
                            "image_url": {
                                "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
                            }
                        }
                    ]
                }
            ],
        )
        
        # Report success
        report_token_status(token_id, "success", api_key=proxy_api_key)
        
        print(completion.choices[0].message)
        return completion
        
    except HfHubHTTPError as e:
        # Report the error
        report_token_status(token_id, "error", str(e), api_key=proxy_api_key)
        raise
    except Exception as e:
        # Report generic error
        report_token_status(token_id, "error", str(e), api_key=proxy_api_key)
        raise

# Usage
if __name__ == "__main__":
    # You need to get your API key from the admin or create a user account
    # See RBAC_README.md for details on user management
    proxy_api_key = "your_proxy_api_key_here"  # Get this from admin
    cerebras_vlm_completion(proxy_api_key)

⚠️ Important: Authentication Required

All client operations now require authentication with the HF-Inferoxy server. This is part of the Role-Based Access Control (RBAC) system that provides secure access to the proxy services.

Getting Your API Key

1. Default Admin User: The system creates a default admin user on first run. Check your server logs or the users.json file for the default admin credentials.

2. Create a User Account: Use the admin account to create a regular user account:

   curl -X POST "http://localhost:8000/admin/users" \
     -H "Authorization: Bearer ADMIN_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{"username": "youruser", "email": "user@example.com", "full_name": "Your Name", "role": "user"}'
   

3. Use the Generated API Key: The response will include an API key that you’ll use in all client operations.

For detailed RBAC setup and user management, see RBAC_README.md.