API Reference

Conversations

Items

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Retrieve an item

client.conversations.items.retrieve(stringitemID, ItemRetrieveParams { conversation_id, include } params, RequestOptionsoptions?): ConversationItem

GET/conversations/{conversation_id}/items/{item_id}

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

ParametersExpand Collapse

itemID: string

params: ItemRetrieveParams { conversation_id, include }

ReturnsExpand Collapse

ConversationItem = Message { id, content, role, 3 more } | ResponseFunctionToolCallItem { id, status, created_by } | ResponseFunctionToolCallOutputItem { id, call_id, output, 6 more } | 25 more

A single item within a conversation. The set of possible types are the same as the output type of a Response object.

One of the following:

Message { id, content, role, 3 more }

A message to or from the model.

ResponseFunctionToolCallItem extends ResponseFunctionToolCall { arguments, call_id, name, 5 more } { id, status, created_by }

A tool call to run a function. See the function calling guide for more information.

ResponseFunctionToolCallOutputItem { id, call_id, output, 6 more }

ResponseFileSearchToolCall { id, queries, status, 2 more }

The results of a file search tool call. See the file search guide for more information.

ResponseFunctionWebSearch { id, action, status, type }

The results of a web search tool call. See the web search guide for more information.

ImageGenerationCall { id, result, status, type }

An image generation request made by the model.

ResponseComputerToolCall { id, call_id, pending_safety_checks, 4 more }

A tool call to a computer use tool. See the computer use guide for more information.

ResponseComputerToolCallOutputItem { id, call_id, output, 4 more }

ResponseToolSearchCall { id, arguments, call_id, 4 more }

ResponseToolSearchOutputItem { id, call_id, execution, 4 more }

AdditionalTools { id, role, tools, type }

ResponseReasoningItem { id, summary, type, 3 more }

A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.

Program { id, call_id, code, 2 more }

ProgramOutput { id, call_id, result, 2 more }

ResponseCompactionItem { id, encrypted_content, type, created_by }

A compaction item generated by the v1/responses/compact API.

ResponseCodeInterpreterToolCall { id, code, container_id, 3 more }

A tool call to run code.

LocalShellCall { id, action, call_id, 2 more }

A tool call to run a command on the local shell.

LocalShellCallOutput { id, output, type, status }

The output of a local shell tool call.

ResponseFunctionShellToolCall { id, action, call_id, 5 more }

A tool call that executes one or more shell commands in a managed environment.

ResponseFunctionShellToolCallOutput { id, call_id, max_output_length, 5 more }

The output of a shell tool call that was emitted.

ResponseApplyPatchToolCall { id, call_id, operation, 4 more }

A tool call that applies file diffs by creating, deleting, or updating files.

ResponseApplyPatchToolCallOutput { id, call_id, status, 4 more }

The output emitted by an apply patch tool call.

McpListTools { id, server_label, tools, 2 more }

A list of tools available on an MCP server.

McpApprovalRequest { id, arguments, name, 2 more }

A request for human approval of a tool invocation.

McpApprovalResponse { id, approval_request_id, approve, 2 more }

A response to an MCP approval request.

McpCall { id, arguments, name, 6 more }

An invocation of a tool on an MCP server.

ResponseCustomToolCall { call_id, input, name, 4 more }

A call to a custom tool created by the model.

ResponseCustomToolCallOutput { call_id, output, type, 2 more }

The output of a custom tool call from your code, being sent back to the model.

Retrieve an item

TypeScript

HTTP

Python

TypeScript

Go

Ruby

Java

CLI Tool

import OpenAI from "openai";
const client = new OpenAI();

const item = await client.conversations.items.retrieve(
  "conv_123",
  "msg_abc"
);
console.log(item);

{
  "type": "message",
  "id": "msg_abc",
  "status": "completed",
  "role": "user",
  "content": [
    {"type": "input_text", "text": "Hello!"}
  ]
}

Returns Examples

{
  "type": "message",
  "id": "msg_abc",
  "status": "completed",
  "role": "user",
  "content": [
    {"type": "input_text", "text": "Hello!"}
  ]
}