Make connector
The NuRoute integration for Make sends chat completions through your NuRoute gateway from any scenario. It's intentionally scoped to just chat completions; everything else (projects, routing config, policy, budgets, API keys) is still managed from the NuRoute dashboard.
Install
The integration is currently private — available to invited users only while it's in early access. Ask your NuRoute admin for an invite link, or reach out at support@nuroute.ai.
Connect your account
Add a module using NuRoute, then create a connection with:
| Field | Value |
|---|---|
| API Key | An aicp-... key from your project's (or org's) API Keys page. Org-wide or project-scoped keys both work. |
| NuRoute Gateway URL | Your gateway's base URL, e.g. https://nuroute.ai — no trailing slash, and without /v1 (that's added automatically). |
Create a Chat Completion
The only module the integration exposes today.
| Field | Description |
|---|---|
| Model | auto (default) lets NuRoute's routing engine pick the best model for the request, or specify a model ID directly (e.g. gpt-4o, claude-sonnet-4-6) |
| User Message | The message to send |
| System Message | Optional instructions the model should follow |
| Temperature / Max Tokens / Provider | Optional. Provider pins a specific upstream provider. Name a model with it: with Model auto, no router runs and the provider serves the first model it lists |
With Model auto, Artemis Task picks the model for each request.
The module returns a flattened result — Completion ID, Model, Reply, Finish Reason,
and a token Usage breakdown (prompt/completion/total) — ready to map into downstream
modules without digging into a raw choices[0].message.content shape.
Which models can I use?
The same catalog as everywhere else. See Providers & Models for the full list, and the dashboard's Model Catalog tab for the live view (providers your admin has connected platform-wide, plus any you've connected yourself via BYOK).