Skip to main content
Cloud models run on RunAnywhere’s hardware instead of the user’s, so you can use models too large for a laptop while keeping the same tools. They bill against prepaid credits, and they are a separate path from on-device inference: nothing routes to the cloud on its own.

​
Signing in

Cloud models need an account on console.runanywhere.ai. To sign in, run:
The browser opens, you approve the request, and the terminal receives its credential. Check it with wally account whoami, and see what you have spent with wally account usage.

​
Running a cloud model

Hosted and local are separate choices, so ask for the cloud one:
--cloud is an opencode flag: it asks for the hosted model rather than one on this machine. Set the model a harness uses by default with wally models default, and see Integrations for the tools Wally can point at a model.

​
API access

The endpoint is OpenAI-compatible, so any OpenAI client works against it. Create a Cloud key in the console, then:
That response is the authoritative list of models you can call. For request fields, streaming, and errors, see the API reference.