Provider & model performance

Continuously sampled from TrustedRouter's monitor regions using a rolling benchmark set of up to 10,000 samples. Time-to-first-token (TTFT), effective throughput, and success rate come from real streaming requests, not vendor claims. Completion rate shows the end-user result. Provider availability excludes failures owned by TrustedRouter, customers, or route configuration, while still reporting those failures under their actual owner. Capacity acceptance measures requests not rejected for provider overload. Effective throughput is provider-reported output tokens divided by complete request time, so buffered delivery cannot inflate the result. Unsupported route and probe-configuration rows are reported separately and do not count as provider downtime. No prompt or output content is ever stored.