Skip to main content
As of Cognigy 2026.6.0, the support for the Completions API for custom LLMs is deprecated. The full removal is planned for Cognigy 2026.24.0. Switch to the `https://api.openai.com/v1/chat/completions` API instead before the removal date.
The gpt-5-1, gpt-5-2, gpt-5-4, gpt-5-4-mini, gpt-5-4-nano, gpt-5-5, gpt-5-6-sol, gpt-5-6-terra, gpt-5-6-luna, gpt-6-sol, gpt-6-luna, and gpt-6-1-sol models default to reasoning.effort: "low" on the Responses API. The reasoning.effort parameter controls how much effort the model uses to think through a request. Higher effort can help the model handle more complex requests, while lower effort can yield faster responses. Supported values, such as "none", "low", "medium", and "high", and their behavior can vary by model and API. Check your LLM provider’s documentation for supported values and behavior.To override this default value, set reasoning.effort in Custom Model Options.The default temperature is 1.0. To override this value, you must set reasoning.effort: "none" and adjust the Temperature parameter or set temperature in Custom Model Options.
To start using an OpenAI model with Cognigy features, follow these steps:
  1. Add models
  2. Apply the model

Restrictions

  • The gpt-5-5, gpt-5-6-sol, gpt-5-6-terra, gpt-5-6-luna, gpt-6-sol, gpt-6-luna, and gpt-6-1-sol models support only the Responses API.
  • The gpt-6-1-sol model doesn’t support the "none" and "minimal" values for reasoning.effort. As a result, you can’t override its default temperature.

Add models

You can add a model using one of the following interfaces:

Add models via GUI

You can add a model provided by OpenAI to Cognigy in Manage > AI & Voice Providers > Language Models. In Generative AI Connection, select an existing connection or click the + button to create one. The connection stores the credentials. To add the model, you’ll need the following parameters:
Apply changes. Check if the connection was set up by clicking Test Connection. You can switch generative models at any time using the Model list without setting up a new connection. For embedding models, the selection is locked because different embedding models can generate incompatible embeddings for Knowledge AI. To switch an embedding, delete the connection and create a new one.

Add models via the API

You can add either a standard or custom model using the Cognigy API POST /v2.0/largelanguagemodels request. Then, test your connection for the created model via the Cognigy API POST /v2.0/largelanguagemodels//test.

Apply the model

To apply a model, follow these steps:
  1. In the navigation menu of the project, go to Manage > AI & Voice Providers > Language Models.
  2. Click Assignments.
  3. Find the capability that should use the model. Capabilities are grouped under Runtime Features, Design-Time, and Knowledge. For Knowledge AI, select a model for Knowledge Search and Answer Extraction. To find models that support these features, refer to Model support by feature.
  4. Select the model in the capability’s list. If no model in the project supports the capability, None is selected and the list shows No model in this project supports this capability.
  5. Click Save changes.

More information

Last modified on November 11, 2026