API Overview

Brivionix provides a fully OpenAI-compatible API. Use any OpenAI SDK or client to call it directly.

Base Information

Item	Value
Base URL	https://brivionix.com
API Path Prefix	/v1
Full API URL	https://brivionix.com/v1
Authentication	Bearer Token
Request Format	JSON (application/json)
Response Format	JSON or SSE (streaming)

Authentication

Include your API Key in the Authorization header:

Authorization: Bearer sk-your-api-key

Create and manage API Keys in the Brivionix Console.

Available Endpoints

Endpoint	Method	Description
/v1/chat/completions	POST	Chat completions (primary)
/v1/models	GET	List available models
/v1/images/generations	POST	Image generation
/v1/embeddings	POST	Text embeddings
/v1/audio/transcriptions	POST	Speech to text
/v1/audio/speech	POST	Text to speech
/v1/rerank	POST	Document re-ranking
/v1/realtime	GET	Real-time conversation (WebSocket)

Quick Test

curl https://brivionix.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{"model": "gpt-5.4-mini", "messages": [{"role": "user", "content": "Hello!"}]}'

Error Codes

HTTP Code	Meaning	Action
200	Success	—
400	Bad request	Check request body format
401	Unauthorized	Check API Key
403	Forbidden	Check token permissions for the model
429	Rate limited	Reduce request frequency, add retry logic
500	Server error	Retry later
503	Service unavailable	Upstream provider issue, retry later

Rate Limiting

When you receive a 429 status, implement exponential backoff:

import time
from openai import OpenAI, RateLimitError

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://brivionix.com/v1",
)

def chat_with_retry(messages, max_retries=3):
    for i in range(max_retries):
        try:
            return client.chat.completions.create(
                model="gpt-5.4-mini",
                messages=messages,
            )
        except RateLimitError:
            wait = 2 ** i
            print(f"Rate limited, retrying in {wait}s...")
            time.sleep(wait)
    raise Exception("Max retries exceeded")

Next Steps

• Chat Completions → — The primary API endpoint
• Supported Models → — All available models
• Get API Key → — Create your token