Skip to main content

OpenAI Model Connector

Last updated on

The OpenAI Model Connector defines OpenAI as the LLM provider and default model for your Worker Agents.


What you will learn

  • Which OpenAI models the connector supports.
  • What each reasoning effort level means for cost and latency.
  • How to configure authentication, the default model, and reasoning effort.
  • How the Harness-managed connector offering works if you do not have model access.

Supported models

The OpenAI Model Connector supports GPT-5.5 with configurable reasoning effort.


Reasoning effort levels

The reasoning effort level controls how much reasoning the model applies before responding, trading latency and cost against depth. Set it on the connector configuration form.

Effort levelDescription
lowFastest, lowest-cost responses for simple tasks
mediumBalanced reasoning and latency for most tasks
highDeeper reasoning for complex tasks
xhighMaximum reasoning depth for the most demanding tasks

Connector configuration

When you create the connector, set the following:

  • Authentication: Provide an OpenAI API key. Reference the key from a Harness secret rather than entering it in plain text.
  • Model Name: Select the default model (GPT-5.5) the agent uses at runtime.
  • Reasoning Effort: Select the default effort level (low, medium, high, or xhigh).

Harness-managed connector

If you do not have access to a model provider, Harness offers a managed LLM connector you can use instead.

Managed connector billing

Until August 2026, usage of the Harness-managed LLM connector is included in your Harness subscription at no additional cost. After August 2026, Harness bills managed LLM connector usage separately, in addition to your Harness subscription.