modelrelay_
Navigate ModelRelay
Get started
Sign in
← All models

Whisper Large v3 Turbo

whisper-large-v3-turbo

Whisper Large v3 Turbo

Accuracy
—
Context
--
Training cutoff
--
Added
2026-09-30

Providers

One route serves Whisper Large v3 Turbo, and every figure below is measured on it. Where the selected window has too little traffic, the figure names what it is based on instead.

Groq only route

whisper-large-v3-turbo

UptimeNo data
Price
$0.04/audio-hour billed per ms of input audio, minimum 10 s per request
Speed
-- needs 30 ModelRelay requests
Context window not published Max output not published Standard retentionwarming · 30m

TTFT is the median time to the first visible answer token over real ModelRelay requests, with a fixed prompt standing in for models that have no traffic yet. Speed ranks by it. Intelligence is the Artificial Analysis Intelligence Index.