> ## Documentation Index > Fetch the complete documentation index at: https://docs.anyapi.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create response > Creates a comprehensive AI response with support for conversations, tools, files, and streaming ## OpenAPI ````yaml /openapi.json post /responses openapi: 3.0.3 info: title: AnyAPI API description: >- Universal API Integration Platform - Connect any API to any API with intelligent data transformation and workflow orchestration. version: 1.0.0 contact: name: AnyAPI Support email: support@anyapi.ai url: https://anyapi.ai/support license: name: MIT url: https://opensource.org/licenses/MIT servers: - url: https://api.anyapi.ai/v1 description: Production server security: - bearerAuth: [] tags: - name: Text description: Generate text completions - name: Images description: Generate and manipulate images - name: Audio description: Generate speech and transcribe audio - name: Music description: List and retrieve model information - name: Video description: Create vector embeddings for text - name: Vision description: Create vector embeddings for text - name: 3D Models description: Create vector embeddings for text - name: Embeddings description: Create vector embeddings for text - name: Files description: Files - name: Batches description: Batches - name: Moderation description: Moderation - name: Other description: Other models paths: /responses: post: tags: - Responses summary: Create response description: >- Creates a comprehensive AI response with support for conversations, tools, files, and streaming operationId: createResponse requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateResponseRequest' examples: Basic: summary: Basic request description: Simple request with model and input text value: model: openai/gpt-4o input: Tell me about AI With temperature: summary: With temperature description: Adjusts creativity level using temperature parameter value: model: openai/gpt-4o input: Write a creative story about a robot temperature: 0.9 With max_tokens: summary: With max_tokens description: Limits the length of the response using max_tokens value: model: openai/gpt-4o input: Explain quantum computing max_tokens: 500 Conversation: summary: Conversation with message history description: Sends full conversation history with multiple messages value: model: openai/gpt-4o conversation: messages: - role: user content: Hello! How are you? - role: assistant content: I'm doing well, thank you! How can I help you today? - role: user content: Tell me about the weather Conversation ID: summary: Using conversation ID description: References existing conversation by ID for context continuity value: model: openai/gpt-4o conversation: conv_abc123xyz input: Can you elaborate on that? New dialog with system message: summary: System message for context description: >- Starts conversation with system message to set assistant behavior value: model: openai/gpt-4o conversation: messages: - role: system content: >- You are a helpful math tutor. Explain concepts clearly. - role: user content: What is calculus? Web Search: summary: Web search tool description: Enables web search capability to find current information value: model: openai/gpt-4o input: What are the latest news about AI today? tools: - type: web_search File Search: summary: File search tool description: Searches through uploaded documents for relevant information value: model: openai/gpt-4o input: >- Find information about quarterly sales in the uploaded documents tools: - type: file_search Code Interpreter: summary: Code interpreter tool description: Executes Python code for calculations and data analysis value: model: openai/gpt-4o input: Calculate the first 10 Fibonacci numbers tools: - type: code_interpreter Multiple tools: summary: Multiple tools combined description: Uses multiple tools together for complex tasks value: model: openai/gpt-4o input: >- Research the latest Python libraries and create a comparison chart tools: - type: web_search - type: code_interpreter All tools: summary: All available tools description: Enables all three tools for maximum capability value: model: openai/gpt-4o input: >- Find recent research papers on machine learning, summarize them, and create visualizations tools: - type: web_search - type: file_search - type: code_interpreter Include web_search sources: summary: Include web search sources description: Returns web search sources in the response value: model: openai/gpt-4o input: What happened in tech news yesterday? tools: - type: web_search include: - web_search Include code_interpreter outputs: summary: Include code outputs description: Returns code execution outputs and generated files value: model: openai/gpt-4o input: Plot a sine wave from 0 to 2π tools: - type: code_interpreter include: - code_interpreter.outputs Include multiple: summary: Include multiple tool outputs description: Returns outputs from multiple tools in the response value: model: openai/gpt-4o input: Research AI trends and create a visualization tools: - type: web_search - type: code_interpreter include: - web_search - code_interpreter.outputs Single image URL: summary: Image from URL description: Analyzes image provided via URL value: model: openai/gpt-4o input: - type: text text: What's in this image? - type: image_url image_url: url: https://example.com/image.jpg Image base64: summary: Image in base64 format description: Analyzes image provided as base64-encoded data value: model: openai/gpt-4o input: - type: text text: Describe this image - type: image_url image_url: url: data:image/jpeg;base64,/9j/4AAQSkZJRg... detail: high Multiple images: summary: Multiple images description: Analyzes and compares multiple images value: model: openai/gpt-4o input: - type: text text: Compare these two images - type: image_url image_url: url: https://example.com/image1.jpg - type: image_url image_url: url: https://example.com/image2.jpg File input: summary: File input for search description: Provides file for analysis with file_search tool value: model: openai/gpt-4o input: Summarize this document files: - file_id: file-abc123 tools: - type: file_search Multiple files: summary: Multiple files description: Analyzes multiple documents together value: model: openai/gpt-4o input: Compare information across these documents files: - file_id: file-abc123 - file_id: file-xyz789 tools: - type: file_search Background processing: summary: Background processing description: Processes request in background for long-running tasks value: model: openai/gpt-4o input: Generate a comprehensive market analysis report tools: - type: web_search - type: code_interpreter background: true Background with callback: summary: Background with webhook description: Background processing with webhook callback when complete value: model: openai/gpt-4o input: Process this large dataset and create visualizations tools: - type: code_interpreter files: - file_id: file-large-dataset background: true webhook_url: https://your-app.com/webhook With metadata: summary: Request with metadata description: Includes custom metadata for tracking and organization value: model: openai/gpt-4o input: Analyze customer feedback metadata: user_id: user_12345 session_id: session_abc request_type: analysis Web research with conversation: summary: Web research in conversation description: Combines conversation context with web search capabilities value: model: openai/gpt-4o conversation: messages: - role: user content: I'm researching renewable energy input: What are the latest developments in solar panel technology? tools: - type: web_search include: - web_search temperature: 0.7 Image analysis with code interpreter: summary: Image + code analysis description: Analyzes images and generates code or visualizations value: model: openai/gpt-4o input: - type: text text: >- Analyze the data in this chart and recreate it with updated styling - type: image_url image_url: url: https://example.com/chart.png tools: - type: code_interpreter include: - code_interpreter.outputs Document analysis with web search: summary: Document + web search description: Compares document content with current online information value: model: openai/gpt-4o input: >- Compare the information in this document with current online sources files: - file_id: file-report-2023 tools: - type: file_search - type: web_search include: - web_search Multi-step research task: summary: Complex multi-step research description: >- Comprehensive research task with system instructions and multiple tools value: model: openai/gpt-4o conversation: messages: - role: system content: >- You are a research assistant. Provide detailed, well-sourced analysis. - role: user content: I need to understand market trends input: >- Research competitors in the EV market, analyze their strategies, and create comparison charts tools: - type: web_search - type: code_interpreter include: - web_search - code_interpreter.outputs max_tokens: 2000 temperature: 0.5 Code analysis with file: summary: Code file analysis description: Reviews code files for bugs and improvements value: model: openai/gpt-4o input: Review this code file for bugs and suggest improvements files: - file_id: file-python-script tools: - type: code_interpreter - type: file_search include: - code_interpreter.outputs Data visualization task: summary: Data visualization description: Creates visualizations and dashboards from data files value: model: openai/gpt-4o input: Create a dashboard with sales trends from the uploaded CSV files: - file_id: file-sales-data-csv tools: - type: code_interpreter include: - code_interpreter.outputs temperature: 0.3 Stream mode: summary: Streaming response description: Streams the response in real-time as it's generated value: model: openai/gpt-4o input: Write a long article about artificial intelligence stream: true Stream with tools: summary: Streaming with tools description: Streams response while using tools value: model: openai/gpt-4o input: Research and write about quantum computing advances tools: - type: web_search include: - web_search stream: true Multi-modal analysis: summary: Multi-modal comprehensive analysis description: Combines images, conversation context, and multiple tools value: model: openai/gpt-4o conversation: messages: - role: system content: You are a data analyst expert input: - type: text text: >- Analyze this chart, search for related market data, and provide insights - type: image_url image_url: url: https://example.com/market-chart.png detail: high tools: - type: web_search - type: code_interpreter include: - web_search - code_interpreter.outputs max_tokens: 3000 Research paper analysis: summary: Research paper analysis description: Analyzes research papers and compares with latest findings value: model: openai/gpt-4o input: Summarize key findings and compare with latest research files: - file_id: file-research-paper-pdf tools: - type: file_search - type: web_search include: - web_search metadata: project: literature-review topic: machine-learning Automated report generation: summary: Automated reporting description: Generates comprehensive reports with charts in background value: model: openai/gpt-4o input: >- Generate a comprehensive weekly report with charts and data analysis files: - file_id: file-weekly-data tools: - type: code_interpreter - type: web_search include: - code_interpreter.outputs - web_search background: true webhook_url: https://your-app.com/reports/webhook metadata: report_type: weekly department: sales Maximum parameters: summary: All available parameters description: Demonstrates maximum capability with all parameters combined value: model: openai/gpt-4o conversation: messages: - role: system content: You are an expert research analyst - role: user content: I need comprehensive market analysis input: - type: text text: >- Analyze this market data, search for competitor information, and create visualizations - type: image_url image_url: url: https://example.com/data-chart.png detail: high files: - file_id: file-market-report tools: - type: web_search - type: file_search - type: code_interpreter include: - web_search - code_interpreter.outputs max_tokens: 4000 temperature: 0.7 stream: false background: false metadata: user_id: user_xyz project: market-analysis priority: high responses: '200': description: Successful response content: application/json: schema: $ref: '#/components/schemas/CreateResponseResponse' text/event-stream: schema: $ref: '#/components/schemas/CreateResponseStreamResponse' '400': description: Bad request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: CreateResponseRequest: type: object required: - model properties: model: type: string description: ID of the model to use example: openai/gpt-4o input: oneOf: - type: string description: Text input for the model - type: array description: Array of content parts (text and/or images) items: oneOf: - $ref: '#/components/schemas/ChatCompletionMessageContentPartText' - $ref: '#/components/schemas/ChatCompletionMessageContentPartImage' conversation: oneOf: - type: string description: Conversation ID to continue an existing conversation - type: object description: Conversation object with message history properties: messages: type: array items: $ref: '#/components/schemas/ChatCompletionMessage' tools: type: array description: List of tools available to the model items: type: object required: - type properties: type: type: string enum: - web_search - file_search - code_interpreter description: Type of tool to enable files: type: array description: List of files to attach to the request items: type: object required: - file_id properties: file_id: type: string description: The ID of the file to use include: type: array description: List of additional data to include in the response items: type: string enum: - web_search - file_search - code_interpreter.outputs max_tokens: type: integer description: Maximum number of tokens to generate minimum: 1 temperature: type: number description: Sampling temperature between 0 and 2 minimum: 0 maximum: 2 default: 1 stream: type: boolean description: Whether to stream the response default: false background: type: boolean description: Process request in background and notify via webhook default: false webhook_url: type: string format: uri description: Webhook URL for background processing notifications metadata: type: object description: Arbitrary metadata to attach to the request additionalProperties: true CreateResponseResponse: type: object required: - id - object - created - model - content properties: id: type: string description: Unique identifier for the response object: type: string enum: - response description: Object type, always 'response' created: type: integer description: Unix timestamp of when the response was created model: type: string description: The model used for generating the response content: type: string description: The generated response content conversation_id: type: string description: ID of the conversation if part of a conversation tools_used: type: array description: List of tools that were used in generating the response items: type: object properties: type: type: string enum: - web_search - file_search - code_interpreter result: type: object description: Tool execution result usage: $ref: '#/components/schemas/CompletionUsage' metadata: type: object description: Metadata attached to the request additionalProperties: true CreateResponseStreamResponse: type: object required: - id - object - created - model - delta properties: id: type: string description: Unique identifier for the response object: type: string enum: - response.chunk description: Object type, always 'response.chunk' created: type: integer description: Unix timestamp of when the response was created model: type: string description: The model used for generating the response delta: type: object description: Incremental content update properties: content: type: string description: Content chunk nullable: true finish_reason: type: string enum: - stop - length - tool_calls - content_filter description: Reason why the stream ended nullable: true ErrorResponse: type: object required: - error properties: error: type: object required: - message - type properties: message: type: string description: A human-readable error message type: type: string description: The type of error code: type: string description: An error code identifying the error type ChatCompletionMessageContentPartText: type: object required: - type - text properties: type: type: string enum: - text text: type: string description: The text content ChatCompletionMessageContentPartImage: type: object required: - type - image_url properties: type: type: string enum: - image_url image_url: type: object required: - url properties: url: type: string format: uri description: Either a URL of the image or the base64 encoded image data detail: type: string enum: - auto - low - high description: Specifies the detail level of the image default: auto ChatCompletionMessage: type: object required: - role - content properties: role: type: string enum: - user - assistant - developer - tool description: The role of the messages author content: oneOf: - type: string description: The contents of the message - type: array description: An array of content parts with a defined type items: $ref: '#/components/schemas/ChatCompletionMessageContentPart' name: type: string description: An optional name for the participant tool_calls: type: array description: The tool calls generated by the model items: $ref: '#/components/schemas/ChatCompletionMessageToolCall' tool_call_id: type: string description: Tool call that this message is responding to CompletionUsage: type: object properties: completion_tokens: type: integer description: Number of tokens in the generated completion prompt_tokens: type: integer description: Number of tokens in the prompt total_tokens: type: integer description: Total number of tokens used in the request required: - completion_tokens - prompt_tokens - total_tokens ChatCompletionMessageContentPart: oneOf: - $ref: '#/components/schemas/ChatCompletionMessageContentPartText' - $ref: '#/components/schemas/ChatCompletionMessageContentPartImage' discriminator: propertyName: type mapping: text: $ref: '#/components/schemas/ChatCompletionMessageContentPartText' image_url: $ref: '#/components/schemas/ChatCompletionMessageContentPartImage' ChatCompletionMessageToolCall: type: object required: - id - type - function properties: id: type: string description: The ID of the tool call type: type: string enum: - function function: type: object required: - name - arguments properties: name: type: string description: The name of the function to call arguments: type: string description: >- The arguments to call the function with, as generated by the model in JSON format securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT description: Bearer token authentication. Get your API key from the dashboard. ````