Get Conversation Item

Get a single item from a conversation with the given IDs.

Options

Conversation Id

The ID of the conversation that contains the item.

Item Id

The ID of the item to retrieve.

Set Include

Enable to set the optional field Include

Include

Additional fields to include in the response. See the include parameter for listing Conversation items above for more information.

Result Format

Specify how the response should be mapped to the table output. The following formats are available:

Structured Table: Returns a parsed table with data split into rows and columns.

• Type: The type of the custom tool call output. Always custom_tool_call_output.
• Id: The unique ID of the custom tool call output in the OpenAI platform.
• Status: The status of the item. One of in_progress, completed, or incomplete.
• Role: The role of the message. One of unknown, user, assistant, system, critic, discriminator, developer, or tool.
• Content: Reasoning text content.
• Call Id: The call ID, used to map this custom tool call output to a custom tool call.
• Name: The name of the custom tool being called.
• Arguments: A JSON string of the arguments passed to the tool.
• Output: The output from the custom tool call generated by your code.
• Queries: The queries used to search for files.
• Results: The results of the file search tool call.
• Action: Execute a shell command on the server.
• Result: The generated image encoded in base64.
• Pending Safety Checks: The pending safety checks for the computer call.
• Acknowledged Safety Checks: The safety checks reported by the API that have been acknowledged by the developer.
• Encrypted Content: The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
• Summary: Reasoning summary content.
• Container Id: The ID of the container used to run the code.
• Code: The code to run, or null if not available.
• Outputs: The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
• Server Label: The label of the MCP server running the tool.
• Tools: The tools available on the server.
• Error: The error from the tool call, if any.
• Approval Request Id: The ID of the approval request being answered.
• Approve: Whether the request was approved.
• Reason: Optional reason for the decision.
• Input: The input for the custom tool call generated by the model.

Raw Response: Returns the raw response in a single row with the following columns:

• body: Response body
• status: HTTP status code

Views

This node has no views

Workflows

• No workflows found

Links

• No links available

Developers