docs/source/guide/prompts_keys.md
There are two approaches to adding a model provider API key.
In one scenario, you get one provider connection per organization, and this provides access to a set of whitelisted models. Examples include:
In the second scenario, you add a separate API key per model. Examples include:
!!! note If you are restricting network access to your resource, you may need to whitelist HumanSignal IP addresses (IP ranges on SaaS) when configuring network security.
Once a model is added via the API key, anyone in the organization who has access to the Prompts feature can select the associated models when executing their prompt.
You can see what API keys you have and add new ones by clicking API Keys in the top right of the Prompts page to open the Model Provider API Keys window:
{% insertmd includes/base_models.md %}
Once you have added a key, all supported models will appear in the base model drop-down when you draft your prompt.
!!! note Models you configure here will also be available in your organization-level providers.
{% insertmd includes/model_keys.md %}