Configure API models and credentials

Open Environment, then Models & connections. Find provider credentials below the engine connections. This section configures API models, separately from subscription-based engines.

Try it · Open Models & connections and scroll to the provider credentials card.

Choose Platform key to use deployment credentials, or My key for your own credentials. Switching sources preserves the other saved key, but does not combine them.

Try it · Expand OpenAI, select Platform key, inspect its configured status, then demonstrate My key.

Enter your provider key under My key. Change the optional base URL only when needed for your endpoint. Save before testing the connection.

Try it · Use a masked demo key, keep the default Base URL, and select Save.

Select Test connection and read the provider result. If it fails, check the selected source, key, and endpoint, then save the correction before retesting.

Try it · Select Test connection; show a simulated failure, correction, save, and successful retest.

Expand Model catalogs & visibility. Working credentials do not make every model visible. Enable the models you want to appear in the chat picker.

Try it · Expand Model catalogs & visibility, then enable one configured model under 可用模型 (Available models).

For OpenRouter or SiliconFlow, refresh the model whitelist, search it, and enable your choices. The provider’s current catalog determines what is available.

Try it · Open the OpenRouter model whitelist, select Refresh, search, and enable a demo model.

Return to a new chat and select the enabled model under API models. In your own workspace, send a simple question to verify the setup.

Try it · Select New chat, open Chat model, select an API model, and illustrate sending a greeting.