Chat Completions API

Overview

Chat Completions API is the most commonly used interface for conversing with AI models.

POST https://api.smai.ai/v1/chat/completions

Request Parameters

Parameter	Type	Required	Description
model	string	Yes	Model name, e.g., `gpt-4.1`
messages	array	Yes	List of conversation messages
temperature	number	No	Sampling temperature, 0-2, default 1
max_tokens	integer	No	Maximum number of tokens to generate
stream	boolean	No	Whether to stream output, default false
top_p	number	No	Nucleus sampling parameter, 0-1

messages Format

[
  { "role": "system", "content": "You are a helpful assistant." },
  { "role": "user", "content": "Hello!" },
  { "role": "assistant", "content": "Hi! How can I help you?" },
  { "role": "user", "content": "What is 2+2?" }
]

Role Description:

system: System prompt, sets the behavior of the AI
user: User message
assistant: AI's reply

Request Example

curl https://api.smai.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "gpt-4.1",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "temperature": 0.7,
    "max_tokens": 1000
  }'

Response Format

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "gpt-4.1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 10,
    "total_tokens": 30
  }
}

Streaming Output

Set stream: true to enable streaming output:

from openai import OpenAI

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

stream = client.chat.completions.create(
    model="gpt-4.1",
    messages=[{"role": "user", "content": "Write a poem"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Supported Models

Chat Completions API supports most models, including:

GPT series: gpt-4.1, gpt-4o, gpt-4-turbo
Claude series: claude-4.5-sonnet, claude-opus-4
Gemini series: gemini-3-pro, gemini-2.5-flash
DeepSeek: deepseek-chat
For more models, please see the model list

Note

Inference models (e.g., gpt-5.2-pro, o3-pro) require the use of the Responses API.