> ## Documentation Index > Fetch the complete documentation index at: https://evo-0136956d.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # 创建聊天对话 > 根据对话历史创建模型响应。支持流式和非流式响应。 兼容 OpenAI Chat Completions API。 ## OpenAPI ````yaml /zh/openapi/relay-api.mintlify.json post /v1/chat/completions openapi: 3.0.1 info: title: AI 调用接口 description: 统一的 AI 模型调用接口，支持 OpenAI、Claude、Gemini、Kling、即梦等多种格式 version: 1.0.0 servers: - url: https://api.nusabase.com description: API Base URL security: - BearerAuth: [] tags: - name: Models description: 获取可用模型列表（支持 OpenAI / Gemini / Anthropic 格式） - name: Chat description: 对话补全与文本补全（OpenAI Chat Completions 兼容） - name: Responses description: OpenAI Responses API（支持工具调用、推理、多轮对话） - name: Realtime description: WebSocket 实时对话（OpenAI Realtime API 兼容） - name: Claude description: Anthropic Claude Messages API 兼容格式 - name: Gemini description: Google Gemini API 兼容格式 - name: Images description: 图片生成与编辑 - name: Video description: 视频生成（OpenAI Sora 兼容格式 + 通用格式） - name: Video / Kling description: Kling 视频生成（文生视频 / 图生视频） - name: Video / Jimeng description: 即梦（Jimeng）视频生成 - name: Audio description: 语音转文字 / 语音翻译 / 文字转语音 - name: Embeddings description: 文本向量嵌入 - name: Rerank description: 文档相关性重排序 - name: Moderations description: 内容安全审核 - name: Not Implemented description: 暂未实现的接口（保留兼容性占位） paths: /v1/chat/completions: post: tags: - Chat summary: 创建聊天对话 description: | 根据对话历史创建模型响应。支持流式和非流式响应。 兼容 OpenAI Chat Completions API。 operationId: createChatCompletion parameters: [] requestBody: content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' required: true responses: '200': description: 成功创建响应 content: application/json: schema: $ref: '#/components/schemas/ChatCompletionResponse' headers: {} '400': description: 请求参数错误 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: {} '429': description: 请求频率限制 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: {} deprecated: false security: - BearerAuth: [] components: schemas: ChatCompletionRequest: type: object required: - model - messages properties: model: type: string description: 模型 ID example: gpt-4 messages: type: array items: $ref: '#/components/schemas/Message' description: 对话消息列表 temperature: type: number minimum: 0 maximum: 2 default: 1 description: 采样温度 top_p: type: number minimum: 0 maximum: 1 default: 1 description: 核采样参数 'n': type: integer minimum: 1 default: 1 description: 生成数量 stream: type: boolean default: false description: 是否流式响应 stream_options: type: object properties: include_usage: type: boolean stop: oneOf: - type: string - type: array items: type: string description: 停止序列 max_tokens: type: integer description: 最大生成 Token 数 max_completion_tokens: type: integer description: 最大补全 Token 数 presence_penalty: type: number minimum: -2 maximum: 2 default: 0 frequency_penalty: type: number minimum: -2 maximum: 2 default: 0 logit_bias: type: object additionalProperties: type: number properties: {} user: type: string tools: type: array items: $ref: '#/components/schemas/Tool' tool_choice: oneOf: - type: string enum: - none - auto - required - type: object properties: type: type: string function: type: object properties: name: type: string response_format: $ref: '#/components/schemas/ResponseFormat' seed: type: integer reasoning_effort: type: string enum: - low - medium - high description: 推理强度 (用于支持推理的模型) modalities: type: array items: type: string enum: - text - audio audio: type: object properties: voice: type: string format: type: string ChatCompletionResponse: type: object properties: id: type: string object: type: string example: chat.completion created: type: integer model: type: string choices: type: array items: type: object properties: index: type: integer message: $ref: '#/components/schemas/Message' finish_reason: type: string enum: - stop - length - tool_calls - content_filter usage: $ref: '#/components/schemas/Usage' system_fingerprint: type: string error: type: object description: 错误信息（非流式时） properties: message: type: string description: 错误消息 type: type: string description: 错误类型 code: type: string description: 错误代码 ErrorResponse: type: object properties: error: type: object properties: message: type: string description: 错误信息 type: type: string description: 错误类型 param: type: string description: 相关参数 nullable: true code: type: string description: 错误代码 nullable: true Message: type: object required: - role - content properties: role: type: string enum: - system - user - assistant - tool - developer description: 消息角色 content: oneOf: - type: string - type: array items: $ref: '#/components/schemas/MessageContent' description: 消息内容 name: type: string description: 发送者名称 tool_calls: type: array items: $ref: '#/components/schemas/ToolCall' tool_call_id: type: string description: 工具调用 ID（用于 tool 角色消息） reasoning_content: type: string description: 推理内容 reasoning: type: string description: 推理内容（部分模型使用） Tool: type: object properties: type: type: string example: function function: type: object properties: name: type: string description: type: string parameters: type: object description: JSON Schema 格式的参数定义 properties: {} ResponseFormat: type: object properties: type: type: string enum: - text - json_object - json_schema json_schema: type: object description: JSON Schema 定义 properties: {} Usage: type: object properties: prompt_tokens: type: integer description: 提示词 Token 数 completion_tokens: type: integer description: 补全 Token 数 total_tokens: type: integer description: 总 Token 数 prompt_tokens_details: type: object properties: cached_tokens: type: integer text_tokens: type: integer audio_tokens: type: integer image_tokens: type: integer completion_tokens_details: type: object properties: text_tokens: type: integer audio_tokens: type: integer reasoning_tokens: type: integer MessageContent: type: object properties: type: type: string enum: - text - image_url - input_audio - file - video_url text: type: string image_url: type: object properties: url: type: string description: 图片 URL 或 base64 detail: type: string enum: - low - high - auto input_audio: type: object properties: data: type: string description: Base64 编码的音频数据 format: type: string enum: - wav - mp3 file: type: object properties: filename: type: string file_data: type: string file_id: type: string video_url: type: object properties: url: type: string ToolCall: type: object properties: id: type: string type: type: string example: function function: type: object properties: name: type: string arguments: type: string securitySchemes: BearerAuth: type: http scheme: bearer description: | 使用 Bearer Token 认证。 格式: `Authorization: Bearer sk-xxxxxx` ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.