OpenAI

Register OpenAI as an LLM provider on SonarQube Server 2026.5, using your own OpenAI API key.

Use the OpenAI provider type to reach OpenAI's own API directly, authenticated with your OpenAI API key.

To select this provider and choose a model for an AI agent, see Selecting a provider and model for an agent; for the steps that apply to every provider type, see LLM providers.

Prerequisites

• An OpenAI API key with access to the models you want to use.

Fields

Field	Required	What to enter
API key	Yes	Your OpenAI API key.

SonarQube Server already knows OpenAI's endpoint (https://api.openai.com/v1), so there's no endpoint field to fill in.

To reach OpenAI through a gateway or proxy instead of its own API, register a Custom provider instead; see Custom.

What happens when you save

SonarQube Server tests the connection when you save, the same as for Custom and Azure AI Foundry. If the test fails, SonarQube Server does not add the provider, and the form reports the problem.

Entering the model identifier

1. Find the model in OpenAI's model catalog.
2. Copy the identifier exactly as OpenAI names it, for example gpt-5.5.
3. Go to the agent's page under Administration > Configuration > AI capabilities, paste the identifier into the model field, and select Save.

If adding the provider fails, see Troubleshooting.