Chat

The Chat API is used for conversational interactions with AI models.

Endpoint

POST https://ai-tokenhub.com/v1/chat/completions

Request Headers

Name	Type	Required	Description
Authorization	string	Yes	Bearer YOUR_API_KEY
Content-Type	string	Yes	application/json

Request Body

Parameter	Type	Required	Default	Description
model	string	Yes	-	Model identifier
messages	array	Yes	-	Array of conversation messages
temperature	number	No	0.7	Generation temperature (0-2)
max_tokens	integer	No	-	Maximum tokens to generate
stream	boolean	No	false	Enable streaming
stop	array/string	No	-	Stop sequences
user	string	No	-	User identifier

Message Roles

• system: System role for setting AI behavior
• user: User role for user input
• assistant: Assistant role for AI responses

Request Example

curl https://ai-tokenhub.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Hello, how are you?"}
    ],
    "temperature": 0.7,
    "max_tokens": 100
  }'

Response Example

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1677858242,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm doing well, thank you for asking."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

Streaming Response

Enable stream: true for Server-Sent Events format.

Error Codes

Code	Description
400	Invalid request parameters
401	Invalid API Key
403	No permission to access this model
429	Rate limit exceeded
500	Internal server error
503	Service unavailable

Use Cases

• Customer Service: Automated responses
• Content Creation: Writing assistance
• Code Assistant: Programming help
• Education: Tutoring and feedback