Population: 1 model this gateway has served · metric: tokens · window: 24 hours · normalization: none. Every chart and every rank on this page is token volume. These are this gateway's own served tokens, never a model's usage anywhere else. Models with no traffic are left out rather than ranked at zero, so the population here is smaller than the 1-model catalogue.
Name, context window, catalogue pricing, Intelligence index, Coding index and Agentic index are read from the API.
Requests served here, tokens served here, week-over-week change and mean request latency are measured by this gateway from the requests it served, read back from POST /api/v1/analytics/query. They describe this deployment only — never a model’s usage anywhere else.
Tokens this gateway served, in hour buckets. Total in window: 27.3M tokens.
Compare authors by the tokens this gateway served for them.
Throughput is blank here — we read the catalogue with a key, so the gate is not what blanks it — the gateway reported no reading for the last 30 minutes, which it does until enough requests have gone through that endpoint to compute one. Nothing is generated to fill it.
Artificial Analysis coding index, read from each model's benchmarks block. Only models that advertise tools and carry a coding index appear — a model without one is left out rather than scored at zero.