Pass IndexThe State of AISign in

Whisper Large v3

Whisper is a general-purpose speech recognition model.

audio → text · made by OpenAI

$0.000008per second
DeepInfra · 2 sellers

Free

Offered at no charge, which is not the same as cheap: a free lane carries a rate limit and can be withdrawn. The prices above are what you pay when it is not available to you.

Sold by 4 ways

SellerLaneRate
Groq apistandard$0.0019per minute$0.0019per minute inconsole.groq.com · read 2026-08-25
DeepInfra aggregatorstandard$0.00048per minuteapi.deepinfra.com · read 2026-08-25
Groq aggregatorfree$0per Mtok in$0per Mtok outconsole.groq.com · read 2026-09-16
Together AI 0 ways
Together AI aggregatornot on the seller's list todaystandard$0.0015per minutedocs.together.ai · read 2026-08-24

Measured 1 standing

PlaceBoardMetricScore
47thof 65Open ASR Leaderboard · English short-formavg (Average WER %)6.0414

About

Whisper Large v3 — a text model from OpenAI, sold by 2 companies from $0.00048 per minute, placed 47th of 65 on Open ASR Leaderboard · English short-form.

It takes audio and returns text, with a context window of 448 tokens. It was published in September 2023, trained on material up to September 2023. The catalogue files it under transcribe and translate. Two companies sell it. The cheapest is $0.00048 per minute at DeepInfra. Beside the standard rate there is a separately routed lane. It stands 47th of 65 on Open ASR Leaderboard · English short-form.

Every current figure

Maker
OpenAI
Register
model
Takes
audio
Returns
text
Context
448 tokens
Published
September 2023
Knowledge to
September 2023
Parameters
1.5 billion
Licence
not read
Sellers
2
Maker's own price
not read
Price
$0.00048 per minute — DeepInfra
Boards
1
Best place
47th of 65 — Open ASR Leaderboard · English short-form

Known as 2 names

openai/whisper-large-v3whisper-large-v3