> ## 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 Format - Responses > - Generic Responses API reference for all compatible models - Server-side context storage: use previous_response_id for multi-turn conversations without manually passing history - Supports streaming and non-streaming responses - Multimodal input: supports text + image + file mixed input - Tool calling: supports Function Calling and built-in tools - Structured output: supports JSON Schema format ## OpenAPI ````yaml openapi/en/openai-format-responses.json POST /v1/responses openapi: 3.1.0 info: title: OpenAI Format - Responses version: '1.0' servers: - url: https://api.aihubmax.com security: - BearerAuth: [] paths: /v1/responses: post: tags: - Text Series > OpenAI Format summary: OpenAI Format - Responses description: > - Generic Responses API reference for all compatible models - Server-side context storage: use previous_response_id for multi-turn conversations without manually passing history - Supports streaming and non-streaming responses - Multimodal input: supports text + image + file mixed input - Tool calling: supports Function Calling and built-in tools - Structured output: supports JSON Schema format operationId: openai-format-responses requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ResponseRequest' examples: simple-input: summary: Simple Text Input description: Pass a text string directly as input value: model: gpt-5.4 input: Explain the design principles of RESTful APIs multi-turn: summary: Multi-turn description: Multi-turn conversation via message list value: model: gpt-5.4 input: - role: developer content: You are a travel planning assistant - role: user content: I want to visit Japan for 5 days with a budget of $3000 - role: assistant content: >- A 5-day Japan trip is a great choice! I suggest focusing on the Kansai region (Osaka-Kyoto-Nara). Do you prefer cultural experiences or food & shopping? - role: user content: Both, but cultural experiences first streaming: summary: Streaming description: Enable streaming output value: model: gpt-5.4 input: Write a short article about AI applications in healthcare stream: true previous-response: summary: Server-side Context (Multi-turn) description: >- Use previous_response_id for multi-turn, no need to manually pass history value: model: gpt-5.4 input: What about the third principle? Can you give an example? previous_response_id: resp_abc123 tool-calling: summary: Tool Use - Weather description: Use Function Calling to invoke external tools value: model: gpt-5.4 input: >- Will it rain in London tomorrow? I'm planning to visit the Tower Bridge tools: - type: function function: name: get_weather description: Get weather forecast for a city parameters: type: object properties: city: type: string description: City name days: type: integer description: Forecast days default: 1 required: - city responses: '200': $ref: '#/components/responses/ResponseSuccess' '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: ResponseRequest: type: object required: - model - input properties: model: type: string description: Model name example: gpt-5.4 input: description: Text input or message list for generating a response oneOf: - type: string description: Text input for generating a response - type: array description: Input message list items: type: object required: - role - content properties: role: type: string description: Role of the message sender enum: - system - user - assistant - developer content: type: string description: Message content stream: type: boolean description: Whether to stream the response default: false temperature: type: number description: Sampling temperature (0-2) minimum: 0 maximum: 2 max_output_tokens: type: integer description: Maximum number of output tokens to generate top_p: type: number description: Nucleus sampling parameter (0-1) minimum: 0 maximum: 1 previous_response_id: type: string description: ID of the previous response, used for multi-turn conversations instructions: type: string description: System-level instructions tools: type: array description: Available tools list items: type: object properties: type: type: string description: Tool type enum: - function - web_search - file_search - code_interpreter function: type: object description: Function definition (when type is function) properties: name: type: string description: Function name description: type: string description: Function description parameters: type: object description: JSON Schema for function parameters required: - name text: type: object description: Text output format configuration properties: format: type: object description: Output format properties: type: type: string description: Format type enum: - text - json_object - json_schema ResponseObject: type: object properties: id: type: string description: Unique response ID example: resp_abc123 object: type: string description: Object type enum: - response created_at: type: integer description: Creation timestamp example: 1757165031 model: type: string description: Model used status: type: string description: The status of the response enum: - completed - failed - in_progress - incomplete example: completed output: type: array description: List of output items items: type: object properties: type: type: string description: Output item type example: message id: type: string description: Output item ID example: msg_abc123 role: type: string description: Role of the output example: assistant content: type: array description: Content list items: type: object properties: type: type: string description: Content type example: output_text text: type: string description: Generated text content example: Hello! How can I help you today? usage: type: object description: Token usage statistics properties: input_tokens: type: integer description: Number of input tokens example: 20 output_tokens: type: integer description: Number of output tokens example: 50 total_tokens: type: integer description: Total number of tokens example: 70 ErrorResponse400: type: object properties: error: type: object properties: message: type: string example: Invalid request parameters type: type: string example: invalid_request_error ErrorResponse401: type: object properties: error: type: object properties: message: type: string example: Invalid API key type: type: string example: authentication_error ErrorResponse403: type: object properties: error: type: object properties: message: type: string example: Access denied type: type: string example: permission_error ErrorResponse429: type: object properties: error: type: object properties: message: type: string example: Rate limit exceeded type: type: string example: rate_limit_error ErrorResponse500: type: object properties: error: type: object properties: message: type: string example: Internal server error type: type: string example: server_error responses: ResponseSuccess: description: Response API success content: application/json: schema: $ref: '#/components/schemas/ResponseObject' BadRequest: description: Bad Request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse400' Unauthorized: description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse401' PaymentRequired: description: Insufficient balance content: application/json: schema: $ref: '#/components/schemas/ErrorResponse400' Forbidden: description: Forbidden content: application/json: schema: $ref: '#/components/schemas/ErrorResponse403' TooManyRequests: description: Too Many Requests content: application/json: schema: $ref: '#/components/schemas/ErrorResponse429' InternalServerError: description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse500' securitySchemes: BearerAuth: type: http scheme: bearer description: | ## All APIs require Bearer Token authentication ## Add to request header: `Authorization: Bearer YOUR_API_KEY` ````