Grok
xAI's Grok chat and Responses API, billed from the dollar cost each response reports rather than a maintained price table.
Where Grok lands
Composite scores out of 10, from benchmark runs where every provider faces the identical task corpus. Rank is within that capability's field. Full method: how we measure.
Grok sits outside the web-access benchmark — the search/scrape/crawl corpora don't exercise a model inference API, so this page carries catalog facts without a scorecard.
The honest pitch
Pick it for Grok's models specifically, where the real per-call cost rides in the response itself instead of a separately kept price list.
Skip it for anything outside the gateway's admitted surface: only a fixed model list and a closed set of request fields are reachable, same as the other model-inference routes here.
About Grok
Grok’s chat and Responses endpoints are reachable through the same policed shape as the other model-inference routes: a maintained model list gates admission, and a closed request-field set is enforced before anything reaches xAI. The distinguishing detail is billing — most Grok responses report their own real dollar cost directly, so that figure is read straight off the response instead of being computed from a separately maintained price table (the table only backs up the rare response that omits it). Files and batches a customer creates are tracked per account, and an account can register its own xAI key to bill that provider directly instead of metering through the gateway.
Reaching it through NativePort
Identical paths, parameters and responses to Grok's own documentation — the gateway holds the upstream credential and meters your balance at Grok's real published usage price.
curl https://api.nativeport.ai/grok/<native-path> \ -H "Authorization: Bearer $NATIVEPORT_API_KEY"