Accounts, models, billing, and privacy
The composer selects the Chat model used for the next request. Settings control authentication, the optional Strategy model, and diagnostic data.
Use Xorin credits
- Select Xorin account in Settings and sign in.
- Select from the models available with your Xorin account.
- View your Xorin credit balance in the header. Its menu also shows the last request cost when available and links to account and credit options.
- Model and asset-generation requests made with this option use Xorin 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 and search providers.
Image, 3D, and audio generation require Xorin credits. Some models are available only when using Xorin credits. Available BYOK models depend on the provider keys you supply.
Chat and Strategy model selection
Select the Chat model beside the interaction mode in the composer. It handles normal requests and executes an approved plan. The selection is stored with the conversation.
Configure an optional Strategy model in Settings. It creates and revises plans in Plan mode and can help the Chat model with difficult decisions in any mode. Selecting None makes the Chat model handle planning and disables separate consultation. Strategy calls may add latency or cost.
Both model pickers group available options into Economy, Standard, and Premium tiers based on Xorin's configured input and output token prices. New installations currently default to GPT-5.6 Sol. Models that require Xorin credits are hidden when using BYOK, and the available catalog can change between releases.
Xorin 2.1.2 expands model selection.
Reasoning effort
GPT-5.6 Sol, Terra, and Luna expose a separate effort selector. Chat effort appears beside the Chat model and belongs to the active conversation. Strategy effort appears below the Strategy model in Settings and applies globally to planning and consultation.
| Effort | When to use it |
|---|---|
| Low | Faster, lighter reasoning. |
| Medium | Balanced; the default for Chat. |
| High | Deeper reasoning; the default for Strategy. |
| Very High | Especially difficult work. |
| Maximum | Deepest reasoning, with the greatest potential latency and credit use. |
Effort controls appear only for supported models. Higher effort can take longer and consume more credits; it does not change the model's authorization or Xorin's safety boundaries.
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 Chat, Strategy, 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 keep/undo outcomes. When using Xorin credits, telemetry required by the Xorin service 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. |
| Show detailed work activity | Shows retained execution steps for successful turns. This is a presentation preference and does not change tool selection, permissions, telemetry, transcripts, or log verbosity. |
| 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>/. When using Xorin
credits, the Xorin service may also process and retain request data
under its applicable privacy and retention policy.
Task reports and consent
Selecting Report on a task opens a request-specific support form. A metadata-only report automatically includes the request ID, Xorin and Unity versions, model, usage, tool status, Plan progress, and error metadata. Report submission requires a signed-in Xorin account and is separate from the Usage telemetry and Chat transcripts settings.
The task's prompt, responses, Plan, and redacted tool details are sent only when you select the task-content checkbox. A screenshot is sent only when you explicitly choose a file or capture the Scene or Game view and leave the preview attached. Consented content is redacted before upload and again before storage.
Descriptions, consented task content, and screenshot content are retained for up to 30 days. The remaining diagnostic report and confirmation ID are retained for up to 180 days. Review the complete task-reporting guide before attaching project content.
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.