Use Poolside models in Hermes

Connect Hermes to Poolside-hosted inference or a self-managed model endpoint. Use OpenRouter if you manage model access through OpenRouter.

Watch the setup video

This video shows the OpenRouter setup path.

You have Hermes installed. For installation options, see Install Hermes.
You have one of the following:
- A Poolside Platform API key. To create one, go to platform.poolside.ai.
- The base URL for your self-managed model endpoint, and its API key if the endpoint requires one.
- An OpenRouter API key with access to Poolside models. To create one, go to OpenRouter API keys.

In a terminal outside an active Hermes session, run:
hermes model
Configure your access method.
- Poolside Platform
- Self-managed Poolside inference
- OpenRouter
1. Choose Custom endpoint (enter URL manually).
2. Enter https://inference.poolside.ai/v1 as the base URL.
3. Enter your Poolside Platform API key.
4. Select or enter a Poolside model. To find model IDs for your access method, see List available models.
5. Complete the remaining prompts.
If you run Poolside model inference on your own infrastructure, use the model’s OpenAI-compatible endpoint at https://<model-hostname>/v1. Use the API key configured for the endpoint, if it requires one.
1. Choose Custom endpoint (enter URL manually).
2. Enter https://<model-hostname>/v1 as the base URL.
3. Enter the API key configured for the model endpoint. If the endpoint does not validate API keys, enter any non-empty value, such as local-test.
4. Select or enter a Poolside model. To find model IDs for your access method, see List available models.
5. Complete the remaining prompts.
1. Choose OpenRouter.
2. Enter your OpenRouter API key.
3. Choose Enter custom model name.
4. Enter an ID from Poolside models on OpenRouter.
5. Complete the remaining prompts.
Start a Hermes session and send a codebase question to confirm Hermes responds with the selected Poolside model.

⌘I