发布/v1/消息

主要的 Anthropic 兼容端点。当所选模型支持时，它支持流、提示缓存、视觉、工具使用和扩展思维。

验证

x-api-key: mg_live_...\nanthropic-version: 2023-06-01\ncontent-type: application/json

最低要求

curl https://api.model-gate.com/v1/messages \
  -H "x-api-key: mg_live_..." \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-opus-4.8",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

高级请求

{
  "model": "claude-opus-4.8",
  "max_tokens": 4096,
  "system": "You are a coding assistant.",
  "thinking": {"type": "enabled", "budget_tokens": 8000},
  "messages": [{"role": "user", "content": "Find the bug in this code."}],
  "tools": [{
    "name": "search_files",
    "description": "Search project files",
    "input_schema": {"type": "object", "properties": {"q": {"type": "string"}}}
  }]
}

想象

{
  "model": "claude-opus-4.8",
  "max_tokens": 1024,
  "messages": [{
    "role": "user",
    "content": [
      {"type": "text", "text": "What is shown in this image?"},
      {"type": "image", "source": {"type": "base64", "media_type": "image/png", "data": "..."}}
    ]
  }]
}

提示缓存

{
  "messages": [{
    "role": "user",
    "content": [
      {"type": "text", "text": "Large reusable context...", "cache_control": {"type": "ephemeral"}},
      {"type": "text", "text": "New question"}
    ]
  }]
}

流媒体

放 "stream": true。响应作为服务器发送的事件返回。

回复

{
  "id": "msg_...",
  "type": "message",
  "role": "assistant",
  "model": "claude-opus-4.8",
  "content": [{"type": "text", "text": "Hello!"}],
  "stop_reason": "end_turn",
  "usage": {"input_tokens": 12, "output_tokens": 8}
}

请求和响应结构遵循 Anthropic Messages API。现有的 Anthropic SDK 通常只需要 base_url 改变。