Accounts, models, billing, and privacy
Settings determine how Xorin authenticates, which model it uses, and what diagnostic data is stored.
Cloud mode
- Sign in to a Xorin account from Settings.
- Select from the models currently enabled for the hosted gateway.
- View your credit balance and open the credit-purchase flow.
- Hosted model and asset-generation requests consume credits according to the service's current pricing.
Bring Your Own Keys
BYOK sends compatible requests directly using keys saved through Unity Editor preferences. The Settings panel currently accepts keys for supported language-model, image, 3D, and search providers.
Not every model or asset workflow is available in both modes. Cloud-only models require Cloud mode, while BYOK workflows depend on the provider keys you supply.
Model and advisor selection
The primary model handles the request. An optional advisor model can be enabled for additional guidance during difficult tasks. Advisor use is bounded and may add latency or cost; selecting None disables it.
The model picker groups available options into Economy, Standard, and Premium tiers. New installations currently default to GPT-5.6 Sol. Cloud-only models are hidden in BYOK mode, and the available catalog can change between releases.
Request cost summaries
After a request completes, Xorin displays its estimated total cost and LLM token count below the response. Hover over the summary for a receipt-style breakdown of applicable executor, advisor, and asset-prompt-refinement model usage, including token categories, calls, iterations, and subtotals.
Generated images, 3D previews and models, and audio appear as separate asset-generation line items when billing information is available. LLM amounts remain estimates; asset line items distinguish confirmed billed charges from charges whose confirmation is still pending. Token totals cover LLM usage only, not image pixels, provider credits, or audio duration.
Telemetry and transcripts
| Setting | What it controls |
|---|---|
| Usage telemetry | Controls local recording of product events such as tool categories, model usage, failures, and accept/undo outcomes. In Cloud mode, service telemetry required for analytics and billing attribution is sent independently of this toggle. |
| Chat transcripts | Local transcript files containing message content, tool calls, parameters, and usage data. |
| Log level | Local Xorin logs at Info, Debug, or Trace. Higher levels contain more sanitized diagnostic detail. |
Telemetry events do not contain full chat transcripts, but some events
can include diagnostic error messages or project asset paths. Local
transcripts are stored under
~/.xorin/chat_history/<project_id>/. Cloud mode may
also process and retain request data under the service's applicable
privacy and retention policy.
Protect your keys
- Do not paste provider keys into chat messages or project files.
- Rotate a key if it is exposed in a screenshot, log, transcript, or repository.