Anthropic Messages

发送对话请求，兼容 Anthropic Claude Messages API 格式。网关内部自动转换为 OpenAI 格式转发，响应转回 Anthropic 格式返回。

请求

POST /v1/messages

Headers

Header	值
Authorization	Bearer sk-你的API密钥
Content-Type	application/json

Body 参数

参数	类型	必填	说明
model	string	✅	模型名称
max_tokens	integer	✅	最大输出 token 数
messages	array	✅	对话消息列表
system	string	❌	系统提示词
stream	boolean	❌	是否流式返回，默认 false
temperature	number	❌	采样温度，0-1
top_p	number	❌	核采样
stop_sequences	array	❌	停止序列

messages 格式

[
  {"role": "user", "content": "你好"},
  {"role": "assistant", "content": "你好！"},
  {"role": "user", "content": "今天天气怎么样？"}
]

支持 content blocks（多模态）：

[
  {
    "role": "user",
    "content": [
      {"type": "text", "text": "描述这张图片"},
      {"type": "image", "source": {"type": "base64", "media_type": "image/jpeg", "data": "..."}}
    ]
  }
]

非流式响应

{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "content": [
    {"type": "text", "text": "你好！有什么可以帮助你的吗？"}
  ],
  "model": "gemini-3-flash",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 10,
    "output_tokens": 15
  }
}

流式响应（SSE）

设置 "stream": true 后，响应使用 Anthropic 标准 SSE 事件格式：

event: message_start
data: {"type":"message_start","message":{"id":"msg_xxx","type":"message","role":"assistant","content":[],"model":"gemini-3-flash"}}

event: content_block_start
data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}

event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"你好"}}

event: content_block_stop
data: {"type":"content_block_stop","index":0}

event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"output_tokens":15}}

event: message_stop
data: {"type":"message_stop"}

示例

curl -X POST https://pico.5884.cn/v1/messages \
  -H "Authorization: Bearer sk-你的API密钥" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-flash",
    "max_tokens": 100,
    "messages": [
      {"role": "user", "content": "用一句话介绍 PicoPapa"}
    ]
  }'

与 OpenAI 格式的关系

/v1/messages 和 /v1/chat/completions 调用的是同一套底层模型和渠道，只是请求/响应格式不同。选择你熟悉的格式即可。