Avery.Software — Native Execution Runtime
RuntimeUse casesPricingHelpBlog
← Back to helprecipe · settings

Connect a cloud LLM provider

2 min · 5 steps

Avery NXR supports 7 cloud providers — Anthropic, OpenAI, Google, Google AI Studio, Azure OpenAI, AWS Bedrock, HuggingFace.

Each provider has its own credential shape: Anthropic/OpenAI/Google take an API key, Azure adds an endpoint URL, Bedrock takes an access key + secret + region. All credentials live in your OS keychain and never travel to Avery's servers.

Steps

  1. Open Settings → AI → Cloud providers.

    The grid lists every supported provider. Frontier APIs are at the top; hosted services below.

    Open Settings →

  2. Click 'Connect' on the provider you want.

    The card expands to show the credential form. Fields are driven by the provider's metadata — masked password inputs for API keys + secret keys, plain text for region / endpoint.

  3. Paste your credentials.

    For Anthropic / OpenAI / Google, just the API key. For Azure OpenAI, both the endpoint URL and the API key. For Bedrock, the region + access-key-id + secret-access-key.

  4. Click 'Test connection'.

    Avery pings the provider's identity endpoint and confirms the credentials work. A green checkmark + identity label means you're good to go.

  5. (Optional) Fetch models.

    Click 'Fetch models' to cache the provider's model catalogue. The dropdown then shows every available model with pricing if the provider exposes it.


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.

Download desktop →