Create Chat Completion

Go to Product

Starting a new project? We recommend trying Responses to take advantage of the latest OpenAI platform features. Compare Chat Completions with Responses.

Creates a model response for the given chat conversation. Learn more in the text generation, vision, and audio guides.

Parameter support can differ depending on the model used to generate the response, particularly for newer reasoning models. Parameters that are only supported for reasoning models are noted below. For the current state of unsupported parameters in reasoning models, refer to the reasoning guide.

Returns a chat completion object, or a streamed sequence of chat completion chunk objects if the request is streamed.

Options

Body

The JSON request body. Pre-filled with an example which is derived from the schema.

Validate JSON
Checks “Body” against the JSON schema of the API. This happens on demand only, i.e. a failed check does not prevent the node from being executed — ultimately, the API itself decides what it accepts.
Body: Validation
Result of the last “Validate JSON” run, i.e. a confirmation or the list of schema violations. Not saved with the node settings.
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.

  • Id: A unique identifier for the chat completion.
  • Choices: A list of chat completion choices. Can be more than one if n is greater than 1.
  • Created: The Unix timestamp (in seconds) of when the chat completion was created.
  • Model: The model used for the chat completion.
  • Service Tier:
  • System Fingerprint:

    This fingerprint represents the backend configuration that the model runs with.

    Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.

  • Object: The object type, which is always chat.completion.
  • Usage: Usage statistics for the completion request.
  • Moderation:

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

  • body: Response body
  • status: HTTP status code

Input Ports

Icon
Configuration data.

Output Ports

Icon
Result of the request depending on the selected Result Format.
Icon
Configuration data (this is the same as the input port; it is provided as passthrough for sequentially chaining nodes to declutter your workflow connections).

Popular Predecessors

Popular Successors

Views

This node has no views

Workflows

Links

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.

Go to Product

Installation

To use this node in KNIME, install the extension OpenAI Nodes from the below update site following our NodePit Product and Node Installation Guide:

v5.12

A zipped version of the software site can be downloaded here.

Plugin provider: NodePit
Plugin version: 2.4.0.202607271506
On NodePit since: 2026-07-27
Last update: 2026-08-12
Tags: Modern UI
KNIME versions: Since v4.7
NodePit Exclusive Only available on NodePit

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!