Overview

The Chat Completions API lets you send messages and get AI responses.

Endpoint

POST /chat/completions

Base URL: https://dev.api-bizora.ai/v1

Authentication

Authorization: Bearer sk_live_YOUR_API_KEY

Parameters

Parameter	Type	Required	Description
model	string	Yes	Must be "bizora"
messages	array	Yes	Array of message objects
stream	boolean	No	Enable streaming (default: false)
deepResearch	boolean	No	Enable deep research mode (default: false)

Message Format

{
  "role": "human",
  "content": "Your message here"
}

Roles:

• human - User message
• ai - Assistant response

Quick Example

import openai

client = openai.OpenAI(
  api_key="sk_live_YOUR_API_KEY",
  base_url="https://dev.api-bizora.ai/v1"
)

response = client.chat.completions.create(
  model="bizora",
  messages=[{"role": "human", "content": "What is section 169?"}]
)

print(response.choices[0].message.content)

Deep Research Mode

Enable deep research for more comprehensive answers:

Python (OpenAI SDK)

response = client.chat.completions.create(
  model="bizora",
  messages=[{"role": "human", "content": "What is section 169?"}],
  extra_body={"deepResearch": True}
)

JavaScript (OpenAI SDK)

const response = await client.chat.completions.create({
model: 'bizora',
messages: [{ role: 'human', content: 'What is section 169?' }],
deepResearch: true
});

HTTP Request

curl https://dev.api-bizora.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk_live_YOUR_API_KEY" \
-d '{
  "model": "bizora",
  "messages": [{"role": "human", "content": "What is section 169?"}],
  "deepResearch": true
}'

Response Format

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "bizora",
  "choices": [{
    "index": 0,
    "message": {
      "role": "ai",
      "content": "Section 169 refers to..."
    },
    "finish_reason": "stop"
  }]
}

Next Steps

• Streaming - Get real-time responses
• HTTP Requests - Use without SDK
• Message Types - Handle custom messages
• Error Handling - Handle errors
• Rate Limits - Understand limits