What a twin, an analysis or a lab theory would cost, before it is called: units, whether it is queued, the limit it breaks.

Prices a call without making it: give the arguments of pull_twin (a twin document, or condition, coupling, planted, field, sessions as a number and seed; nothing at all is the default twin), of pull_analyse (a sessions document, with prereg, replication, surrogates and pairs) or of pull_lab (a theory, one-dimensional or with a model, or reference skyrme or hopfion). The engine counts the document without running it: a twin's or an analysis's sessions, events, draws, work and an estimate of CPU-seconds (cpu_pairs and cpu_note say which part of a group's estimate repeats for each pair), a lab theory's lattice, the steps priced and its CPU-seconds. The answer adds what this service makes of the count: for, the call it priced; units, what that call would be charged, null when it would be refused (a queued call's price is the engine's count, so a lattice or a system generator, which the formula that routes a call cannot see, is priced as it will be); queued, whether it would be queued (202) rather than answer at once; within_limits, and when it is false the limit it breaks. A one-dimensional theory is counted too and is queued like any theory (an ordinary one at 1 unit), and the one-dimensional references, which are not counted, are refused here by name. Runs and renders nothing. Costs no units.