Ship
Inference optimization endpoint targeting lower-cost execution while preserving reference-model behavior.
Ship is a beta inference endpoint from Thesean AI that sits between an application and its provider/reference model, optimizing requests across models, tools, and harnesses to reduce inference cost while preserving the reference model's capabilities and behavior.
Recent stories
Ship reads pull requests, tests affected flows against the deployed app, and reproduces bugs from Slack or Linear. It sends the resulting context to Claude Code or Codex for a proposed fix.
Martian launched Ship, a beta endpoint that sits between an app and its reference model and routes each request through cheaper paths while aiming to preserve behavior. Martian says the beta targets 50% lower cost.