> ## Documentation Index > Fetch the complete documentation index at: https://docs.cubeuaeai.com/llms.txt > Use this file to discover all available pages before exploring further. # deepseek-v4-pro > Generate a model response from the conversation. ## OpenAPI ````yaml en/api-reference/model-api/deepseek/openapi/deepseek-v4-pro/openapi.yaml POST /v1/chat/completions openapi: 3.1.0 info: title: DeepSeek V4 Pro description: Call DeepSeek V4 Pro version: 1.0.0 servers: - url: https://ai.cubeuaeai.com security: - bearerAuth: [] paths: /v1/chat/completions: post: summary: Chat completion description: Generate a model response from the conversation. operationId: createChatCompletionDeepseekV4Pro requestBody: required: true content: application/json: schema: type: object required: - model - messages properties: model: type: string enum: - deepseek-v4-pro description: model ID example: deepseek-v4-pro messages: type: array minItems: 1 description: List of conversation messages. items: type: object required: - role - content properties: role: type: string enum: - system - user - assistant - tool content: type: string name: type: string description: >- Participant name, used to distinguish different participants with the same role. prefix: type: boolean description: >- When true, the model continues generation using this message as a prefix. tool_call_id: type: string description: >- Required for tool messages. The ID of the tool call this message responds to. example: - role: user content: Hello! thinking: type: object nullable: true description: Enable or disable thinking mode. properties: type: type: string enum: - enabled - disabled description: '`enabled` turns on thinking mode.' reasoning_effort: type: string enum: - high - max - low - medium description: Controls reasoning intensity. max_tokens: type: integer minimum: 1 description: Maximum number of tokens to generate. response_format: type: object properties: type: type: string enum: - text - json_object default: text description: 'Set `{"type": "json_object"}` to enable JSON mode.' stop: oneOf: - type: string - type: array items: type: string description: Sequences that stop generation. Up to 16. stream: type: boolean default: false description: When true, results are streamed back via SSE. stream_options: type: object description: Streaming options. Only valid when stream is true. properties: include_usage: type: boolean description: >- When true, usage statistics are returned before the stream ends. temperature: type: number minimum: 0 maximum: 2 default: 1 description: >- Sampling temperature. Higher values make the output more random. example: 1 top_p: type: number minimum: 0 maximum: 1 default: 1 description: Nucleus sampling threshold. tools: type: array description: >- A list of tools the model can call. Currently only function calling is supported. items: type: object properties: type: type: string enum: - function function: type: object required: - name properties: name: type: string description: Function name. description: type: string description: Description of what the function does. parameters: type: object description: Function parameters in JSON Schema format. strict: type: boolean description: When true, enables strict mode. tool_choice: oneOf: - type: string enum: - none - auto - required - type: object properties: type: type: string enum: - function function: type: object required: - name properties: name: type: string description: >- Controls tool-calling behavior: `none`, `auto`, `required`, or a specific function. frequency_penalty: type: number minimum: -2 maximum: 2 default: 0 description: Deprecated by DeepSeek. Passing this has no effect. presence_penalty: type: number minimum: -2 maximum: 2 default: 0 description: Deprecated by DeepSeek. Passing this has no effect. user_id: type: string maxLength: 512 pattern: ^[a-zA-Z0-9\-_]+$ description: >- Custom user ID, used for content-safety processing and KVCache isolation. responses: '200': description: Response generated successfully content: application/json: schema: $ref: '#/components/schemas/ChatCompletion' '400': description: Invalid request parameters content: application/json: schema: type: object properties: error: type: object properties: message: type: string type: type: string code: type: string '401': description: Unauthorized '429': description: Rate limit exceeded components: schemas: ChatCompletion: type: object properties: id: type: string example: chatcmpl-abc123 object: type: string example: chat.completion created: type: integer description: Unix timestamp model: type: string example: deepseek-v4-pro choices: type: array items: type: object properties: index: type: integer message: type: object properties: role: type: string example: assistant content: type: string nullable: true example: Hello! How can I help you? reasoning_content: type: string nullable: true description: Reasoning process in thinking mode. tool_calls: type: array nullable: true items: type: object properties: id: type: string type: type: string enum: - function function: type: object properties: name: type: string arguments: type: string finish_reason: type: string nullable: true enum: - stop - length - content_filter - tool_calls - insufficient_system_resource - null matched_stop: type: string nullable: true usage: type: object properties: prompt_tokens: type: integer completion_tokens: type: integer total_tokens: type: integer prompt_tokens_details: type: object nullable: true properties: cached_tokens: type: integer audio_tokens: type: integer text_tokens: type: integer completion_tokens_details: type: object properties: reasoning_tokens: type: integer accepted_prediction_tokens: type: integer rejected_prediction_tokens: type: integer system_fingerprint: type: string nullable: true description: Backend configuration fingerprint. securitySchemes: bearerAuth: type: http scheme: bearer description: >- Authenticate with a Bearer token. After creating an API key in the Cube AI console, pass it as `Bearer YOUR_API_KEY` in the Authorization header. ````