Hermes Agent | Northern Inference docs

Use Northern Inference as the Hermes Agent backend over exact sovereign Canadian routes with custody records for government, defence and regulated teams.

Northern Inference is a sovereign Canadian AI API for government, defence, health and regulated teams, including organizations under the Controlled Goods Program. Every route carries PIPEDA-aligned Canadian data residency, an exact path to the latest frontier and open-weight models, and a per-request chain-of-custody record.

Before you start

Create an API key. In the portal, open Keys and click Create Key. Your key starts with ni_live_.
Add credit. New accounts start with a balance of $0, and every request is refused until you add credit. Open Billing and click Buy credits.
Pick a model. Northern Inference model names end in a tier tag, for example claude-sonnet-4-6-t4. See them all on the Models page.

Install Hermes Agent

Mac, Linux and WSL2:

curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

Windows PowerShell:

iex (irm https://hermes-agent.nousresearch.com/install.ps1)

Desktop apps for Mac and Windows are also available from the Hermes Agent site. The source is on GitHub.

Connect Hermes to Northern Inference

Run the model setup:

hermes model

Choose Custom endpoint (self-hosted / VLLM / etc.) and enter:

Setting	Value
URL	`https://northerninference.ca/v1`
API key	your `ni_live_` key
Model	`claude-sonnet-4-6-t4`

Hermes saves this in the right place for your operating system. Start Hermes and send a message. It appears in the portal under Usage within a few seconds.

Or edit the config file

The setup writes this block to config.yaml in your Hermes folder: ~/.hermes/config.yaml on Mac and Linux, and %LOCALAPPDATA%\hermes\config.yaml on Windows. You can also write it yourself. If the file already has a model: block, replace that block with this one.

model:
  default: claude-sonnet-4-6-t4
  provider: custom
  base_url: https://northerninference.ca/v1
  api_key: ni_live_YOUR_KEY_HERE

Good models to start with

Model	Notes
`claude-sonnet-4-6-t4`	A strong general choice
`mistral-large-2402-t3`	Runs in Canada (Tier 3)

Use the exact name from the Models page, including its case.

If a model name is not recognized

Northern Inference answers with HTTP 404 and Model 'X' is not a route this key can call. It never swaps in a different model. Use a name from the Models page, or type ni-models as a message to list the models your key can call. If the name is a model your key can call without its tier tag, such as claude-sonnet-4-6, the answer also asks Did you mean claude-sonnet-4-6-t4?. If the name is the same model on more than one route your key can call, the answer is HTTP 400 ambiguous_model_route and names each route; use one of them.

Troubleshooting

What you see	What to do
401 or "Invalid API key"	Check that the key starts with `ni_live_` and has no extra spaces. Create a new one in the portal under Keys if needed.
402 `Insufficient credits. Add credits in the portal under Billing (https://northerninference.ca/portal/?page=billing) to continue.`	Add credit in the portal under Billing.
404 `Model 'X' is not a route this key can call.`	Use a name from the Models page, or type `ni-models`.
Requests do not show up in Usage	Hermes is using another provider. Run `hermes model` again and choose the custom endpoint, or check that `provider` is `custom` and `base_url` is exactly `https://northerninference.ca/v1`.

Spend limits

To cap spending for a project, create a separate key in the portal under Keys with a Max spend per day limit, and use that key in Hermes.