Main APIs

1. Chat Completions

Interact with AI models for single-turn and multi-turn conversations.

Endpoint: POST /v1/chat/completions

Key Parameters:

Parameter	Type	Required	Description
model	string	Yes	Model name, e.g. gpt-4, claude-3-sonnet
messages	array	Yes	List of conversation messages
max_tokens	number	No	Maximum response length, default 1024
temperature	number	No	Creativity control, 0-2, default 1
stream	boolean	No	Whether to stream response, default false

Message Format:

{
  "role": "user|assistant|system",
  "content": "Message content"
}

Complete Request Example:

{
  "model": "gpt-4",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant"},
    {"role": "user", "content": "Write a Python bubble sort algorithm"}
  ],
  "max_tokens": 500,
  "temperature": 0.7
}

Response Format:

{
  "id": "chatcmpl-123",
  "object": "chat.completion", 
  "created": 1677858242,
  "model": "gpt-4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Here's the AI response content..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 100, 
    "total_tokens": 120
  }
}

2. List Available Models

View the list of currently available AI models.

Endpoint: GET /v1/models

Response Example:

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4",
      "object": "model",
      "created": 1677858242,
      "owned_by": "openai"
    },
    {
      "id": "claude-3-sonnet-20240229", 
      "object": "model",
      "created": 1677858242,
      "owned_by": "anthropic"
    }
  ]
}