modelbenchmark.io

Whisper

OpenAI · whisper-large-v3

Compare

Speech transcription model for accurate audio-to-text and captioning workflows

Specification

most-agreed values

Context
0
Max output
0
Released
2023-09-01
Knowledge cutoff
2023-09
Retires
Open weights
yes
Input
audio
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.003
Output
free

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
scaleway$0.003free08K
privatemode-ai$0.0162free4484K
groq00
scaleway · scalewayfree