OpenRouter's Batch API trades predictable response time for lower inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → prices. Developers submit work together and allow the provider a 24-hour completion window, generally receiving a 50% discount on tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → charges, with discounts varying by model. That suits backlogs such as document labeling or evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → runs that can wait. The launch report says the median completed batch during its two-week beta took seven minutes, but that observation is not a seven-minute delivery promise.
Terms in this piece · Glossary
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
