Arbiter is a premium Orrery route for coding tasks where evidence matters. The experience is simple: ask Orrery to run work, review what happened, see the usage it consumed, and decide whether to trust the result.
What subscribers see
Inside Orrery, Arbiter appears as a hosted model route named arbiter-0.1-beta. It can be selected from Nexus alongside DeepSeek API and Doubleword hosted routes. Subscribers see usage meters, run receipts, and proof/boundary summaries where the app supports them.
The route is designed for agentic coding workflows: planning, editing, follow-up fixes, and review. It does not replace your own testing, code review, security review, or backups.
Latent-style signals vs token-only generation
Most chat models produce the next token directly from the visible prompt and context. Arbiter is positioned differently in Orrery: it is tested as a coding route that values structured run signals such as task state, review evidence, and verifier-style feedback, then turns those signals into ordinary agent output.
The practical difference for subscribers is simple: Arbiter is meant for coding work where a final answer is not enough. Nexus should show the prompt, route, run summary, usage, proof, and boundary receipts so the user can inspect the result instead of trusting a raw completion.
Beta evidence
Current internal beta evidence includes a 92/100 frozen local projection on the first 100 SWE-bench Verified tasks. Orrery treats that as a release-readiness signal, not a leaderboard entry or a guarantee about any individual subscriber run. Larger matched evaluations will be published only when they are ready.
Availability
Arbiter access is available for Orrery Pro, Max, and Ultra subscriber testing through hosted credits when the beta route is online. Signed-out users, unsubscribed accounts, and canceled or unpaid accounts cannot use hosted Arbiter credits.
The exact capacity, latency, quotas, model mix, and availability may change during the beta.
Use safely
Treat Arbiter output like any other AI-generated code: inspect it, run tests, review security implications, and keep backups. Orrery can help organize evidence, but you remain responsible for what you accept, run, and ship.