modelbenchmark.io

whisper

OpenAI · whisper

Specification

most-agreed values

Context

—

Max output

—

Released

—

Knowledge cutoff

—

Retires

2026-12-15

Open weights

—

Input

—

Output

—

Rate limits

Requests per minute

720

Available from 2 hosts

Host	In $/M	Out $/M	Cache rd	Cache wr	Context	Output	Retires
azure	—	—	—	—	—	—	2026-12-15
azure_ai	—	—	—	—	—	—	2026-12-15