> ## Documentation Index > Fetch the complete documentation index at: https://docs.aihubmax.com/llms.txt > Use this file to discover all available pages before exploring further. # OpenAI 格式 - 调用工具对话 > - 适用于所有兼容 OpenAI 格式模型的通用 Chat Completions API（含工具调用） - 工具调用：支持 Function Calling，定义模型可调用的工具 - 结构化输出：支持 JSON Object / JSON Schema 格式 - 多模态输入：支持文本 + 图像混合输入 - 支持流式和非流式响应 ## OpenAPI ````yaml openapi/zh/openai-format-chat-completions.json POST /v1/chat/completions openapi: 3.1.0 info: title: OpenAI Format - Tool Calling Chat version: '1.0' servers: - url: https://api.aihubmax.com security: - BearerAuth: [] paths: /v1/chat/completions: post: tags: - Text Series > OpenAI Format summary: OpenAI Format - Tool Calling Chat description: | - 适用于所有兼容 OpenAI 格式模型的通用 Chat Completions API（含工具调用） - 工具调用：支持 Function Calling，定义模型可调用的工具 - 结构化输出：支持 JSON Object / JSON Schema 格式 - 多模态输入：支持文本 + 图像混合输入 - 支持流式和非流式响应 operationId: openai-format-chat-completions requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' examples: single-turn: summary: 单轮对话 description: 最基础的单轮问答 value: model: gpt-5.4 messages: - role: user content: 用 Python 写一个快速排序算法 multi-turn: summary: 多轮对话 description: 包含上下文的多轮对话 value: model: gpt-5.4 messages: - role: system content: 你是一位资深的后端工程师 - role: user content: 我的 API 响应时间从 200ms 增长到了 2s，可能是什么原因？ - role: assistant content: |- 响应时间大幅增长通常有几个常见原因： 1. 数据库查询变慢（缺少索引、数据量增长） 2. 外部服务调用超时 3. 内存泄漏导致 GC 频繁 4. 网络延迟增加 你能提供更多信息吗？比如是所有接口都变慢还是特定接口？ - role: user content: 只有涉及用户列表查询的接口变慢了 streaming: summary: 流式响应 description: 启用流式输出，实时获取生成内容 value: model: gpt-5.4 messages: - role: user content: 详细解释 TCP 三次握手的过程 stream: true with-image: summary: 带图片 description: 发送图片让模型分析（视觉理解） value: model: gpt-5.4 messages: - role: user content: - type: text text: 这个架构图有什么问题？请指出潜在的性能瓶颈 - type: image_url image_url: url: >- https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/1200px-Cat03.jpg tool-calling-weather: summary: 工具调用 - 天气查询 description: 让模型调用天气查询工具获取实时天气信息 value: model: gpt-5.4 messages: - role: user content: 北京今天天气怎么样？适合户外跑步吗？ tools: - type: function function: name: get_weather description: 获取指定城市的当前天气信息 parameters: type: object properties: city: type: string description: 城市名称 unit: type: string enum: - celsius - fahrenheit description: 温度单位 required: - city tool-calling-search: summary: 工具调用 - 网页搜索 description: 让模型调用搜索工具查找最新信息 value: model: gpt-5.4 messages: - role: user content: 帮我查一下 GPT-5 最新的发布消息 tools: - type: function function: name: web_search description: 在互联网上搜索信息 parameters: type: object properties: query: type: string description: 搜索关键词 num_results: type: integer description: 返回结果数量 default: 5 required: - query tool-calling-database: summary: 工具调用 - 数据查询 description: 让模型调用数据查询工具获取业务数据 value: model: gpt-5.4 messages: - role: user content: 查一下上个月销售额最高的前5个产品 tools: - type: function function: name: query_database description: 查询业务数据库获取数据 parameters: type: object properties: query: type: string description: SQL 查询语句 database: type: string enum: - sales - inventory - users description: 目标数据库 required: - query - database responses: '200': $ref: '#/components/responses/ChatCompletionSuccess' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '402': $ref: '#/components/responses/PaymentRequired' '403': $ref: '#/components/responses/Forbidden' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' components: schemas: ChatCompletionRequest: type: object required: - model - messages properties: model: type: string description: 模型名称，如 gpt-5.4、deepseek-chat 等 example: gpt-5.4 messages: type: array description: 对话消息列表 items: type: object required: - role - content properties: role: type: string description: 消息发送者的角色 enum: - system - user - assistant - tool content: type: string description: 消息内容 stream: type: boolean description: 是否流式返回响应 default: false temperature: type: number description: 采样温度 (0-2) minimum: 0 maximum: 2 max_tokens: type: integer description: 最大生成token数 top_p: type: number description: 核采样参数 (0-1) minimum: 0 maximum: 1 frequency_penalty: type: number description: 频率惩罚 (-2 到 2) minimum: -2 maximum: 2 presence_penalty: type: number description: 存在惩罚 (-2 到 2) minimum: -2 maximum: 2 tools: type: array description: 可用工具列表 items: type: object properties: type: type: string enum: - function function: type: object properties: name: type: string description: 函数名称 description: type: string description: 函数描述 parameters: type: object description: 函数参数的 JSON Schema required: - name tool_choice: description: 工具选择策略 oneOf: - type: string enum: - none - auto - required - type: object properties: type: type: string enum: - function function: type: object properties: name: type: string required: - name response_format: type: object description: 响应格式 properties: type: type: string description: 响应格式类型 enum: - text - json_object - json_schema stop: description: 停止序列 oneOf: - type: string - type: array items: type: string 'n': type: integer description: 生成数量 ChatCompletionResponse: type: object properties: id: type: string description: 唯一补全ID example: chatcmpl-abc123 object: type: string description: 对象类型 enum: - chat.completion created: type: integer description: 创建时间戳 example: 1757165031 model: type: string description: 使用的模型 choices: type: array items: type: object properties: index: type: integer description: 选项索引 example: 0 message: type: object properties: role: type: string example: assistant content: type: string example: Hello! How can I help you today? finish_reason: type: string description: 生成停止原因 enum: - stop - length - content_filter - tool_calls example: stop usage: type: object properties: prompt_tokens: type: integer description: 提示token数 example: 20 completion_tokens: type: integer description: 补全token数 example: 50 total_tokens: type: integer description: 总token数 example: 70 ErrorResponse400: type: object properties: error: type: object properties: message: type: string example: 请求参数无效 type: type: string example: invalid_request_error ErrorResponse401: type: object properties: error: type: object properties: message: type: string example: API密钥无效 type: type: string example: authentication_error ErrorResponse403: type: object properties: error: type: object properties: message: type: string example: 访问被拒绝 type: type: string example: permission_error ErrorResponse429: type: object properties: error: type: object properties: message: type: string example: 请求频率超限 type: type: string example: rate_limit_error ErrorResponse500: type: object properties: error: type: object properties: message: type: string example: 服务器内部错误 type: type: string example: server_error responses: ChatCompletionSuccess: description: 对话补全响应 content: application/json: schema: $ref: '#/components/schemas/ChatCompletionResponse' BadRequest: description: 请求错误 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse400' Unauthorized: description: 未授权 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse401' PaymentRequired: description: 余额不足 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse400' Forbidden: description: 禁止访问 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse403' TooManyRequests: description: 请求过多 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse429' InternalServerError: description: 服务器内部错误 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse500' securitySchemes: BearerAuth: type: http scheme: bearer description: | ## 所有接口均需要使用Bearer Token进行认证 ## 使用时在请求头中添加： `Authorization: Bearer YOUR_API_KEY` ````