Runic
AI SETTINGS

Runic's Claude, or your own Anthropic, OpenAI or Google key

The owner decides whose key pays for AI; an account can bring its own key from any of the three providers and every AI feature runs on it, same prompts, same self-checks.

Try it free →Read the docs

What it is

AI in Runic has always been proxied: the browser never talks to a model provider, the server does, and the platform key lives in the server environment. AI settings keeps that shape and adds a second source of keys. The owner opens the staff console, chooses the AI tab and picks one of three modes. Runic's Claude runs everyone on the platform key and ignores stored keys. Users bring their own key turns AI off for an account until it stores a key. The third mode uses the platform key by default and switches an account to its own key the moment one is stored.

An account manages its key under Settings → AI (avatar menu → Settings). The screen explains the mode in force, and when a key is allowed it offers three providers, Anthropic, OpenAI and Google, a key field, and two optional model fields.

How a key is saved

Save sends the key once. The server calls the provider's model list with it: a refusal comes back as "OpenAI rejected that key", an outage as a request to try again in a moment, and nothing is stored in either case. If you named a model, it has to appear in that list; a name the key cannot see is refused with the name in the message. Only then is the key encrypted with AES-256-GCM under a server-side secret and written with a seven-character hint such as sk-…7890. The response carries the hint, the provider and the model picks, never the key.

From then on every AI request for that account decrypts the key inside the request that spends it. The key is deleted with the account, and the data export lists the provider and the hint only.

Which model answers

Runic routes each action to a tier rather than a model: autocomplete and archive summaries on the fast tier, chat, inline edits and the clarifying questions on the main tier, whole-document work such as Create with AI and the build spec on the strongest tier. Each provider maps the tiers to its own defaults, Claude Haiku 4.5, Sonnet 5 and Opus 5 on Anthropic, gpt-5-mini and gpt-5 on OpenAI, Gemini 2.5 Flash and Pro on Google. The two fields in AI settings override the fast tier and the main tiers. The label under each chat reply names the model that actually answered.

Providers that reason before answering get the effort dialled to the tier and a floored output budget, so an eighty-token autocomplete is not spent entirely on thinking. Web research in the chat uses each provider's own search tool.

What does not change

The prompts are identical on every provider, and so is everything wrapped around them: the deterministic parse and structural audit after a generation, the single bounded repair pass that is kept only when it scores better, the diff-and-apply flow for proposals, the checkpoints. Hourly limits still apply per account. The only difference an account sees is the model label and the bill, which goes to its own provider account.

How to use it

  1. Owner picks the mode
    Staff console, AI tab: Runic's Claude, users bring their own key, or Runic's key unless an account stored its own. The change is audited.
  2. Open AI settings
    Avatar menu → Settings → AI. The section states the mode in force and shows the key form when a key is allowed.
  3. Pick a provider and paste the key
    Anthropic, OpenAI or Google. Leave the model fields empty for the defaults or name models the key can use.
  4. Save
    Runic checks the key against the provider, refuses a bad key or an unavailable model, then stores it encrypted and shows a masked hint.
  5. Use AI as before
    Chat, Create with AI, inline edits and autocomplete run on the stored key. Change or Remove from the same screen.

Commands & shortcuts

Runic's ClaudePlatform key for everyone; stored keys are ignored
Users bring their own keyAI is off for an account until it stores a key
Runic's Claude, own key overridesPlatform key by default, a stored key takes over
Fast modelAutocomplete and archive summaries
Main modelChat, edits, questions, generation and the build spec

Tips

  • Leave the model fields empty unless you have a reason; the defaults match how Runic tunes each action.
  • A key that works in the provider's console but is refused here usually lacks access to the model you named, so try saving without the model fields first.
  • Teams on a shared provider account can each store the same key; usage then shows up under one bill with Runic's per-account limits on top.
  • If the owner switches the workspace to Runic's Claude, your stored key stays saved but idle, and comes back into use if the mode changes again.

Questions

Can Runic staff see my key?

No. It is encrypted at rest under a server-side secret, decrypted only inside the request that uses it, and the interfaces (settings screen, admin console, data export) only ever carry a masked hint.

Which providers are supported?

Anthropic (Messages API), OpenAI (Responses API) and Google Gemini (generateContent). The same prompts run on all three.

Do my documents get stored by the provider?

Runic sends requests with storage disabled where the provider offers the option, and never sends more than the request needs. What each provider retains beyond that is governed by your agreement with them.

What happens when my key stops working?

AI replies say the provider rejected the key and point you to AI settings. Nothing else in the editor is affected.