API
OpenAI-compatible, fully documented.
Standard chat completions with streaming, authenticated with a Cloud key from the console. Any client that takes a base URL works unchanged.
https://inference.runanywhere.ai/v1API
Standard chat completions with streaming, authenticated with a Cloud key from the console. Any client that takes a base URL works unchanged.
https://inference.runanywhere.ai/v1The rule
Cloud and local are explicit choices. Nothing moves a request between them silently.
Questions
It's how you reach RunAnywhere's biggest models without leaving your own workflow. Sign in once with RCLI, tell it to run in the cloud, and you're talking to an OpenAI-compatible endpoint. Your local SDKs and accelerators still handle everything that fits on your device, and RCLI never moves a request between the two on its own.
We keep the current lineup and pricing in the docs instead of here, since it changes as we add capacity. Every model bills per million tokens and speaks the same streaming chat-completions format, so switching between them is a config change, not a rewrite.
Yes. Point your existing OpenAI client, curl command, or SDK at Wally's base URL and model ID, and it works. Nothing new to install or learn.
Most people never touch a key. Run rcli login, approve it in your browser with Google or GitHub, and the credential comes back to RCLI on its own. A raw key only matters if you're calling the endpoint directly with curl or another SDK outside RCLI.
We keep prompt and response bodies for 30 days, purely for abuse review and billing audits. Usage metadata like token counts and timestamps sticks around longer, since we need it for billing. There is no way to turn body storage off today. Full details are on the privacy page.