Skip to main content
POST
/
chat
/
claude
/
v1
/
messages
创建消息 (Anthropic 兼容)
curl --request POST \
  --url https://api.mountsea.ai/chat/claude/v1/messages \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "claude-sonnet-4-6",
  "messages": [
    {
      "role": "user",
      "content": "Hello, Claude!"
    }
  ],
  "max_tokens": 4096,
  "system": "You are a helpful coding assistant.",
  "stream": true,
  "temperature": 1,
  "top_p": 1,
  "top_k": 40,
  "stop_sequences": [
    "<string>"
  ],
  "tools": [
    {}
  ],
  "tool_choice": {}
}
'

​
💡 About

此接口兼容 Anthropic Messages API 格式，适用于：
  • Claude Code CLI 工具直接接入
  • Anthropic SDK（Python / TypeScript）调用
  • 任何支持 Anthropic API 格式的客户端
Base URL: https://api.mountsea.ai/chat/claude，与 OpenAI 兼容 API 的 Base URL 不同，请注意区分。

​
🤖 Claude Code 配置

设置以下环境变量即可让 Claude Code 使用我们的 API： 
export ANTHROPIC_API_KEY="your-api-key"
export ANTHROPIC_BASE_URL="https://api.mountsea.ai/chat/claude"
claude

​
💡 Quick Examples

import anthropic

client = anthropic.Anthropic(
    api_key="your-api-key",
    base_url="https://api.mountsea.ai/chat/claude"
)

# Basic message
message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=4096,
    system="You are a helpful assistant.",
    messages=[
        {"role": "user", "content": "Hello, Claude!"}
    ]
)

print(message.content[0].text)
Streaming:
with client.messages.stream(
    model="claude-sonnet-4-6",
    max_tokens=4096,
    messages=[{"role": "user", "content": "Tell me a story"}]
) as stream:
    for text in stream.text_stream:
        print(text, end="")
Install:
pip install anthropic

​
📤 Response Format

​
Non-streaming Response

{
  "id": "msg_xxx",
  "type": "message",
  "role": "assistant",
  "model": "claude-sonnet-4-6",
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I help you today?"
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 25,
    "output_tokens": 10
  }
}

​
Streaming Response (SSE)

event: message_start
data: {"type":"message_start","message":{"id":"msg_xxx","type":"message","role":"assistant","model":"claude-sonnet-4-6"}}

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":"Hello"}}

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

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

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

​
🔧 Supported Models

ModelDescription
claude-4.5Claude 4.5，综合能力强
claude-opus-4-6Claude Opus 4.6，最强推理能力
claude-sonnet-4-6Claude Sonnet 4.6，性能与速度平衡
claude-haiku-4-5-20251001Claude Haiku 4.5，轻量快速

​
🔧 API Reference

The interactive API form below is auto-generated from OpenAPI spec.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
model
enum<string>
required

模型名称

Available options:
claude-4.5,
claude-opus-4-6,
claude-haiku-4-5-20251001,
claude-sonnet-4-6
Example:

"claude-sonnet-4-6"

​
messages
object[]
required

消息列表

Example:
[
  {
    "role": "user",
    "content": "Hello, Claude!"
  }
]
​
max_tokens
number
required

最大 token 数

Example:

4096

​
system
string

系统提示词

Example:

"You are a helpful coding assistant."

​
stream
boolean

是否流式输出

Example:

true

​
temperature
number | null

温度 (0-1)

Example:

1

​
top_p
number | null

Top P

Example:

1

​
top_k
number | null

Top K

Example:

40

​
stop_sequences
string[]

停止序列

​
tools
object[]

工具列表

​
tool_choice
object

工具选择策略

Response

成功