> ## Documentation Index > Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt > Use this file to discover all available pages before exploring further. # deepseek-v4.1-flash > 使用 DeepSeek V4.1 Flash 根据文本或图像输入生成响应。 ## OpenAPI ````yaml zh/api-reference/model-api/deepseek/openapi/deepseek-v4-1-flash/openapi.yaml POST /v1/chat/completions openapi: 3.1.0 info: title: DeepSeek V4.1 Flash description: 通过 AnyFast OpenAI 兼容的 Chat Completions API 调用 DeepSeek V4.1 Flash。 version: 1.0.0 servers: - url: https://www.anyfast.ai security: - bearerAuth: [] paths: /v1/chat/completions: post: summary: 创建对话补全 description: 使用 DeepSeek V4.1 Flash 根据文本或图像输入生成响应。 operationId: createChatCompletionDeepseekV41Flash requestBody: required: true content: application/json: schema: type: object required: - model - messages properties: model: type: string enum: - deepseek-v4.1-flash description: AnyFast 模型 ID。 example: deepseek-v4.1-flash messages: type: array minItems: 1 description: 对话消息列表。图像内容只能放在 user 消息中。 items: type: object required: - role - content properties: role: type: string enum: - system - user - assistant - tool content: oneOf: - type: string - type: array items: oneOf: - type: object required: - type - text properties: type: type: string enum: - text text: type: string - type: object required: - type - image_url properties: type: type: string enum: - image_url image_url: type: object required: - url properties: url: type: string description: >- JPEG、PNG、GIF 或 WebP 图像的公网 HTTP(S) URL 或 Base64 data URL。 detail: type: string enum: - low - high - original - auto default: auto reasoning_content: type: string nullable: true description: 上一轮助手推理内容。使用工具进行多轮对话时需要原样回传。 name: type: string tool_call_id: type: string description: tool 消息必填，对应的工具调用 ID。 tool_calls: type: array items: $ref: '#/components/schemas/ToolCall' thinking: type: object nullable: true description: 思考模式配置。默认开启思考模式。 properties: type: type: string enum: - enabled - disabled default: enabled reasoning_effort: type: string enum: - none - low - high - max default: high description: 思考开关与推理强度。`none` 关闭思考；该字段位于请求顶层，不属于 `thinking` 对象。 max_tokens: type: integer minimum: 1 maximum: 393216 description: 最大生成 Token 数。 response_format: type: object properties: type: type: string enum: - text - json_object default: text description: 使用 `json_object` 开启 JSON 模式，同时需要在提示词中明确要求输出 JSON。 stop: oneOf: - type: string - type: array maxItems: 16 items: type: string stream: type: boolean default: false description: 是否通过 SSE 流式返回消息增量。 stream_options: type: object properties: include_usage: type: boolean default: false temperature: type: number minimum: 0 maximum: 2 default: 1 description: 开启思考模式时该参数会被忽略。 top_p: type: number minimum: 0 maximum: 1 default: 1 description: 思考模式下小于 0.95 的值按 0.95 处理；非思考模式下有效值为 1.0。 tools: type: array items: type: object required: - type - function properties: type: type: string enum: - function function: type: object required: - name - parameters properties: name: type: string description: type: string parameters: type: object description: 使用 JSON Schema 描述的函数参数。 strict: type: boolean tool_choice: oneOf: - type: string enum: - none - auto - required - type: object required: - type - function properties: type: type: string enum: - function function: type: object required: - name properties: name: type: string frequency_penalty: type: number minimum: -2 maximum: 2 default: 0 description: 为兼容性保留；开启思考模式时不生效。 presence_penalty: type: number minimum: -2 maximum: 2 default: 0 description: 为兼容性保留；开启思考模式时不生效。 user_id: type: string maxLength: 512 pattern: ^[a-zA-Z0-9\-_]+$ description: 用于内容安全和缓存隔离的稳定终端用户标识。 examples: text: summary: 文本输入 value: model: deepseek-v4.1-flash messages: - role: user content: 解释 B 树索引如何加速数据库查询。 max_tokens: 1024 vision: summary: 图像输入 value: model: deepseek-v4.1-flash messages: - role: user content: - type: text text: 描述这张图像并读取其中可见的文字。 - type: image_url image_url: url: https://example.com/chart.png thinking: summary: 思考模式 value: model: deepseek-v4.1-flash messages: - role: user content: 找出并解释这个算法中的错误。 thinking: type: enabled reasoning_effort: high responses: '200': description: 对话补全创建成功 content: application/json: schema: $ref: '#/components/schemas/ChatCompletion' '400': description: 请求参数无效 content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: 未认证 '429': description: 请求频率超限 components: schemas: ToolCall: type: object properties: id: type: string type: type: string enum: - function function: type: object properties: name: type: string arguments: type: string ChatCompletion: type: object required: - id - object - created - model - choices - usage properties: id: type: string example: chatcmpl-example object: type: string enum: - chat.completion created: type: integer description: Unix 秒级时间戳。 model: type: string example: deepseek-v4.1-flash choices: type: array items: type: object properties: index: type: integer message: type: object properties: role: type: string enum: - assistant content: type: string nullable: true reasoning_content: type: string nullable: true description: 开启思考模式时生成的推理内容。 tool_calls: type: array nullable: true items: $ref: '#/components/schemas/ToolCall' finish_reason: type: string nullable: true enum: - stop - length - content_filter - tool_calls - insufficient_system_resource - null usage: type: object properties: prompt_tokens: type: integer completion_tokens: type: integer total_tokens: type: integer prompt_tokens_details: type: object properties: cached_tokens: type: integer prompt_cache_hit_tokens: type: integer prompt_cache_miss_tokens: type: integer Error: type: object properties: error: type: object properties: message: type: string type: type: string code: type: string securitySchemes: bearerAuth: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.