API endpoint https://northerninference.ca/v1 Use this as the base URL in every integration.

Zed

Use Northern Inference in the Zed editor with exact sovereign routes and Canadian data residency 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

  1. Create an API key. In the portal, open Keys and click Create Key. Your key starts with ni_live_.
  2. 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.
  3. 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.

Connect Zed to Northern Inference

  1. Open the command palette and run agent: open settings.
  2. In LLM Providers, click Add Provider and choose an OpenAI-compatible provider.
  3. Fill in the fields with the values in the table below.
  4. Enter your ni_live_ key in the provider's settings.
  5. Open the Agent Panel, choose claude-sonnet-4-6-t4 in its model list and send a message. It appears in the portal under Usage within a few seconds.
FieldValue
Provider namenorthern-inference
API URLhttps://northerninference.ca/v1
Model IDclaude-sonnet-4-6-t4
Context window200000

Or edit the settings file

Run zed: open settings file from the command palette and add:

{
  "language_models": {
    "openai_compatible": {
      "northern-inference": {
        "api_url": "https://northerninference.ca/v1",
        "available_models": [
          {
            "name": "claude-sonnet-4-6-t4",
            "display_name": "Claude Sonnet 4.6 (Northern Inference)",
            "max_tokens": 200000
          }
        ]
      }
    }
  }
}

Do not put your key in this file. Enter it in agent: open settings under the provider, or set it in the environment variable NORTHERN_INFERENCE_API_KEY (Zed builds the name from the provider name).

In Zed, max_tokens is the model's context window, not the length of the reply. To add more models, add more entries with exact names from the Models page.

Images

Zed treats a model on a custom provider as text-only unless you say otherwise. To send images to a model that accepts them, add "capabilities": { "images": true } to that model's entry. The Vision and capabilities page lists which models accept images.

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.

Troubleshooting

What you seeWhat to do
The model is missing from the Agent PanelCheck the provider in agent: open settings. The model ID must be an exact name from the Models page.
401The key is wrong or missing. Enter it again in the provider's settings.
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.

Spot a problem? Write to support at northerninference dot ca.

↑