AI / LLM
The Seven20 platform includes features to enable the use of AI and LLMs (Large Language Models) to assist with the recruitment process or automations within Seven20.
All functionality within Seven20 is provided via a Bring Your Own Model (BYOM) approach. This means that Seven20 does not provide direct access to any models or AI functionality out of the box, but instead provides the tools to build custom AI functionality. Any implementer is expected to provide their own credentials to access any models they wish to use, which may result in additional third-party charges based on the chosen model.
A packaged permission set LLM_User includes the relevant permissions for using the LLMs (does not grant the named credentials access).
Out of the box model support
Seven20 supports the following models out of the box. These models are available for use in the platform and can be used in automations, flows, and other features without any additional development work (outside of integrating them into your automations).
| Model Provider | Model Name | Notes |
|---|---|---|
| OpenAI | GPT-4.1 | |
| OpenAI | GPT-4.1-mini | |
| OpenAI | GPT-4.1-nano | |
| OpenAI | GPT-4o | |
| OpenAI | GPT-4o-mini | |
| Azure OpenAI | GPT-4.1 | Utilises the next generation API |
| Azure OpenAI | GPT-4.1-mini | Utilises the next generation API |
| Azure OpenAI | GPT-4.1-nano | Utilises the next generation API |
| Azure OpenAI | GPT-4o | Utilises the next generation API |
| Azure OpenAI | GPT-4o-mini | Utilises the next generation API |
If you wish to use a different model than listed above, or use a custom trained one, consider implementing a custom model instead.
Seven20 commits to supporting these models for the foreseeable future. However, we cannot guarantee that these models will always be available or supported by the model provider. When a model is deprecated by the model provider, Seven20 will also deprecate it. Ensure you regularly check the model provider's documentation for any changes to the models you are using.