LongCat API开放平台接口文档

概述

LongCat API开放平台专为LongCat-Flash-Chat模型提供AI模型代理服务，同时兼容OpenAI和Anthropic API格式。本文档遵循标准API格式约定。

基础URL

生产环境端点: https://api.longcat.chat

认证

所有API请求都需要在Authorization头中使用API密钥进行认证：

Authorization: Bearer YOUR_API_KEY

接口

聊天补全

POST /openai/v1/chat/completions

使用OpenAI兼容格式创建聊天补全。

请求头

Authorization: Bearer YOUR_API_KEY（必填）
Content-Type: application/json

请求体

字段	类型	必填	说明
`model`	string	是	模型标识符（仅支持LongCat-Flash-Chat）
`messages`	array	是	消息对象数组，仅允许文本输入
`stream`	boolean	否	是否以流式返回响应（默认：false）
`max_tokens`	integer	否	生成的最大token数，默认为1024
`temperature`	number	否	采样温度，范围0到1
`top_p`	number	否	核采样参数

消息对象

字段	类型	必填	说明
`role`	string	是	消息作者角色。必须为以下之一： • `system` - 设置助手行为和上下文 • `user` - 人类用户消息 • `assistant` - AI助手消息（用于会话历史）
`content`	string	是	消息内容。简单文本消息字符串。

请求示例

{
  "model": "LongCat-Flash-Chat",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello, how are you?"
    }
  ],
  "stream": false,
  "max_tokens": 150,
  "temperature": 0.7
}

响应（非流式）

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "LongCat-Flash-Chat",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm doing well, thank you for asking. How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 15,
    "total_tokens": 35
  }
}

响应（流式）

当stream: true时，响应以Server-Sent Events (SSE)返回：

Content-Type: text/event-stream

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"LongCat-Flash-Chat","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"LongCat-Flash-Chat","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"LongCat-Flash-Chat","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

data: [DONE]

Anthropic消息

POST /anthropic/v1/messages

使用Anthropic的Claude API格式创建消息。

请求头

Authorization: Bearer YOUR_API_KEY（必填）
Content-Type: application/json

请求体

字段	类型	必填	说明
`model`	string	是	Claude模型名称
`messages`	array	是	消息对象数组
`max_tokens`	integer	否	生成的最大token数
`stream`	boolean	否	是否以流式返回响应（默认：false）
`temperature`	number	否	采样温度，范围0到1
`top_p`	number	否	核采样参数
`system`	string	否	用于设置上下文的系统消息

消息对象

字段	类型	必填	说明
`role`	string	是	消息作者角色。必须为以下之一： • `user` - 人类用户消息 • `assistant` - Claude助手消息（用于会话历史）注意：系统消息通过`system`参数单独传递
`content`	string	是	消息内容。仅支持文本消息字符串

请求示例

{
  "model": "LongCat-Flash-Chat",
  "max_tokens": 1000,
  "messages": [
    {
      "role": "user",
      "content": "Hello, LongCat"
    }
  ],
  "stream": false,
  "temperature": 0.7
}

响应（非流式）

{
  "id": "msg_123",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I help you today?"
    }
  ],
  "model": "LongCat-Flash-Chat",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 10,
    "output_tokens": 8
  }
}

响应（流式）

当stream: true时，响应遵循Anthropic的SSE格式：

Content-Type: text/event-stream

event: message_start
data: {"type": "message_start", "message": {"id": "msg_123", "type": "message", "role": "assistant", "content": [], "model": "LongCat-Flash-Chat", "stop_reason": null, "stop_sequence": null, "usage": {"input_tokens": 10, "output_tokens": 0}}}

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_delta
data: {"type": "message_delta", "delta": {"stop_reason": "end_turn", "stop_sequence": null}, "usage": {"output_tokens": 8}}

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

错误响应

API使用常规HTTP响应码指示成功或失败：

HTTP状态码

状态码	状态名称	说明
`200`	OK	请求成功
`400`	Bad Request	请求参数无效或JSON格式错误
`401`	Unauthorized	API密钥无效或缺失
`403`	Forbidden	API密钥无权限访问请求资源
`429`	Too Many Requests	超出速率限制
`500`	Internal Server Error	服务器遇到意外情况
`502`	Bad Gateway	上游服务器响应无效
`503`	Service Unavailable	服务器暂时不可用

错误响应格式

所有错误返回如下结构的JSON对象：

{
  "error": {
    "message": "人类可读的错误描述",
    "type": "error_type_identifier",
    "code": "specific_error_code",
    "param": "parameter_name_if_applicable"
  }
}

错误类型与代码

错误类型	错误代码	HTTP状态	说明
`authentication_error`	`invalid_api_key`	401	提供的API密钥无效
`authentication_error`	`missing_api_key`	401	未提供API密钥
`permission_error`	`insufficient_quota`	403	API密钥配额不足
`invalid_request_error`	`invalid_parameter`	400	参数值无效
`invalid_request_error`	`missing_parameter`	400	缺少必填参数
`invalid_request_error`	`invalid_json`	400	JSON格式无效
`rate_limit_error`	`rate_limit_exceeded`	429	短时间内请求过多
`server_error`	`internal_error`	500	服务器内部错误

错误响应示例

API密钥无效

{
  "error": {
    "message": "Invalid API key provided",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}

缺少必填参数

{
  "error": {
    "message": "Missing required parameter: 'messages'",
    "type": "invalid_request_error",
    "code": "missing_parameter",
    "param": "messages"
  }
}

超出速率限制

{
  "error": {
    "message": "Rate limit exceeded. Please try again in 60 seconds",
    "type": "rate_limit_error",
    "code": "rate_limit_exceeded"
  }
}

速率限制

速率限制按API密钥执行。超出限制时会收到429状态码。

SDK兼容性

本API设计兼容：

OpenAI Python SDK（用于/openai/端点）
Anthropic Python SDK（用于/anthropic/端点）
任何支持相应API格式的HTTP客户端

示例

使用OpenAI Python SDK

import openai

# 配置LongCat-Flash-Chat API
openai.api_base = "https://api.longcat.chat/openai"
openai.api_key = "your-api-key"

response = openai.ChatCompletion.create(
    model="LongCat-Flash-Chat",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

使用Anthropic Python SDK

import anthropic

# 配置LongCat-Flash-Chat API
client = anthropic.Anthropic(
    api_key="Bearer your-api-key",
    base_url="https://api.longcat.chat"
)
default_headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer your-api-key",
    }


message = client.messages.create(
    model="LongCat-Flash-Chat",
    max_tokens=150,
    messages=[
        {"role": "user", "content": "Hello, LongCat!"}
    ]
)

使用cURL

# OpenAI风格请求
curl -X POST https://api.longcat.chat/openai/v1/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "LongCat-Flash-Chat",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": false
  }'

# Anthropic风格请求
curl -X POST https://api.longcat.chat/anthropic/v1/messages \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "LongCat-Flash-Chat",
    "max_tokens": 1000,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

📋 需要帮助？ 请查阅我们的FAQ获取常见问题和故障排查指南。