Connect a cloud provider (for Build + optional Runtime)
2 min · 3 steps
Add API credentials in one place — referenced by Build, Runtime, and Local Failover.
The Cloud Models Config tab is the canonical place to set credentials + pick a default model per cloud provider. Once configured, the AI Model for Build, AI Model for Runtime, and Local Failover sections reference these providers by name. Keys live in your local keystore — they never leave the machine via the WebSocket.
Steps
- Open Settings → AI → Cloud Models Config.
Find your provider (Anthropic, OpenAI, Google, Azure, Bedrock, HuggingFace, Google AI Studio) + click Connect.
- Paste your API key + test the connection.
Avery probes the provider's `/v1/models` endpoint to confirm the key works + populate the model picker.
- Pick the default model for this provider.
Used downstream as the picker default in Build and Runtime cloud mode.
Live recipes need the desktop
This article is a static preview. The in-app Help sidecar inside Avery NXR can fire each step against your live project — install the desktop to use it interactively.