OpenAI Automation

Automate your OpenAI API workflows -- generate text with the Responses API (including multimodal image+text inputs and structured JSON outputs), create embeddings for search and clustering, generate images with DALL-E and GPT Image models, and list available models.

Toolkit docs: composio.dev/toolkits/openai

---

Setup

1. Add the Composio MCP server to your client: https://rube.app/mcp
2. Connect your OpenAI account when prompted (API key authentication)
3. Start using the workflows below

---

Core Workflows

1. Generate a Response (Text, Multimodal, Structured)

Use OPENAI_CREATE_RESPONSE for one-shot model responses including text, image analysis, OCR, and structured JSON outputs.

Tool: OPENAI_CREATE_RESPONSE
Inputs:
  - model: string (required) -- e.g., "gpt-5", "gpt-4o", "o3-mini"
  - input: string | array (required)
    Simple: "Explain quantum computing"
    Multimodal: [
      { role: "user", content: [
        { type: "input_text", text: "What is in this image?" },
        { type: "input_image", image_url: { url: "https://..." } }
      ]}
    ]
  - temperature: number (0-2, optional -- not supported with reasoning models)
  - max_output_tokens: integer (optional)
  - reasoning: { effort: "none" | "minimal" | "low" | "medium" | "high" }
  - text: object (structured output config)
    - format: { type: "json_schema", name: "...", schema: {...}, strict: true }
  - tools: array (function, code_interpreter, file_search, web_search)
  - tool_choice: "auto" | "none" | "required" | { type: "function", function: { name: "..." } }
  - store: boolean (false to opt out of model distillation)
  - stream: boolean

Structured output example: Set text.format to { type: "json_schema", name: "person", schema: { type: "object", properties: { name: { type: "string" }, age: { type: "integer" } }, required: ["name", "age"], additionalProperties: false }, strict: true }.