API Reference

Conversations

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Create a conversation

conversations.create(ConversationCreateParams**kwargs) -> Conversation

POST/conversations

Create a conversation.

ParametersExpand Collapse

items: Optional[Iterable[ResponseInputItemParam]]

Initial items to include in the conversation context. You may add up to 20 items at a time.

metadata: Optional[Metadata]

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

ReturnsExpand Collapse

class Conversation: …

id: str

The unique ID of the conversation.

created_at: int

The time at which the conversation was created, measured in seconds since the Unix epoch.

formatunixtime

metadata: object

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

object: Literal["conversation"]

The object type, which is always conversation.

Create a conversation

Python

HTTP

Python

TypeScript

Go

Ruby

Java

CLI Tool

from openai import OpenAI
client = OpenAI()

conversation = client.conversations.create(
  metadata={"topic": "demo"},
  items=[
    {"type": "message", "role": "user", "content": "Hello!"}
  ]
)
print(conversation)

{
  "id": "conv_123",
  "object": "conversation",
  "created_at": 1741900000,
  "metadata": {"topic": "demo"}
}

Returns Examples

{
  "id": "conv_123",
  "object": "conversation",
  "created_at": 1741900000,
  "metadata": {"topic": "demo"}
}