API 端点

端点总览

smai.ai 提供多种 API 端点，满足不同场景的需求。

对话接口

OpenAI 通用接口

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

已适配所有模型，推荐使用此接口。

from openai import OpenAI

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

response = client.chat.completions.create(
    model="gpt-4.1",
    messages=[{"role": "user", "content": "你好！"}]
)

Claude 原生接口

https://api.smai.ai/v1/messages

适配 Anthropic Claude 原生 API 格式。

import anthropic

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

message = client.messages.create(
    model="claude-4.5-sonnet",
    max_tokens=1024,
    messages=[{"role": "user", "content": "你好！"}]
)

Gemini 原生接口

https://api.smai.ai/v1beta/models/模型名称:generateContent

适配 Google Gemini 原生 API 格式。

curl "https://api.smai.ai/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: sk-your-api-key" \
  -d '{
    "contents": [{
      "parts": [{"text": "你好！"}]
    }]
  }'

图片生成接口

OpenAI / 豆包 / 千问图片生成

https://api.smai.ai/v1/images/generations

from openai import OpenAI

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

response = client.images.generate(
    model="dall-e-3",
    prompt="一只可爱的猫咪",
    size="1024x1024"
)

Midjourney 生图接口

https://api.smai.ai/mj/submit/imagine

curl https://api.smai.ai/mj/submit/imagine \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "prompt": "a beautiful sunset over the ocean --ar 16:9"
  }'

视频生成接口

https://api.smai.ai/v1/videos

支持 Sora 等视频生成模型。

curl https://api.smai.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "sora-2",
    "prompt": "一只猫在草地上奔跑"
  }'

音频接口

Suno 音乐生成

https://api.smai.ai/suno/submit/music

curl https://api.smai.ai/suno/submit/music \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "prompt": "一首轻快的流行音乐",
    "style": "pop"
  }'

文本转语音 (TTS)

https://api.smai.ai/v1/audio/speech

from openai import OpenAI

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

response = client.audio.speech.create(
    model="tts-1",
    voice="alloy",
    input="你好，欢迎使用 smai.ai！"
)

response.stream_to_file("output.mp3")

其他端点

端点	用途
`https://api.smai.ai/v1/models`	获取可用模型列表
`https://api.smai.ai/v1/responses`	推理模型专用端点

端点选择指南

graph TD
    A[选择端点] --> B{接口类型?}
    B -->|对话| C{模型厂商?}
    B -->|图片| D[/v1/images/generations]
    B -->|视频| E[/v1/videos]
    B -->|音频| F[/v1/audio/speech]
    C -->|通用| G[/v1/chat/completions]
    C -->|Claude 原生| H[/v1/messages]
    C -->|Gemini 原生| I[/v1beta/models/:generateContent]

Chat Completions API

对话补全接口详解

Responses API

推理模型接口详解

API 端点

Chat Completions API

Responses API

目录