API Overview

Introduction

smai.ai provides an API interface that is fully compatible with OpenAI, allowing you to connect directly using any SDK or application that supports the OpenAI API.

Basic Information

Item	Value
Base URL	`https://api.smai.ai`
API Version	v1
Authentication Method	Bearer Token
Request Format	JSON
Response Format	JSON

API Endpoints

Endpoint List

View all available API endpoints

Chat Completions

Conversation completion API, the most commonly used interface

Responses API

Endpoint dedicated to inference models

Error Handling

Error codes and handling methods

Authentication

All API requests require the API token to be included in the request header:

Authorization: Bearer sk-your-api-key

Security Reminder

Do not expose your API token in client-side code. It is recommended to proxy API requests through a backend service.

Quick 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!"}
    ]
  }'

Request Limits

Rate Limit: Different request rate limits apply based on account level
Concurrency Limit: There is a limit on the number of simultaneous requests
Token Limit: The number of tokens per request is limited by the model

If you encounter limits, please try again later or contact customer service to upgrade your account.