Whisper
Whisper (model ID whisper-1) is a general-purpose speech recognition model trained on diverse audio, usable as a multitask model for multilingual speech recognition, speech translation, and language identification.
audio → text · made by OpenAI
$0.006per minute
OpenAI · 3 sellers
Sold by 4 ways
| Seller | Lane | Rate |
|---|---|---|
| OpenAI api | standard | $0.006per minutedevelopers.openai.com · read 2026-08-24 |
| Microsoft Azure AI cloud | standard | $0.006per minute in$0.006per minute outraw.githubusercontent.com · read 2026-10-31 |
| Cloudflare 0 ways | $0.0005 | |
| Cloudflare aggregatornot on the seller's list today | standard | $0.0005per minute$0.00048per minute indevelopers.cloudflare.com · read 2026-08-25 |
| Vercel AI Gateway aggregator | standard | $0.0001per Mtok inai-gateway.vercel.sh · read 2026-08-25 |
About
Whisper — a text model from OpenAI, sold by 3 companies from $0.0001 per Mtok in.
It takes audio and returns text, with a context window of 448,000 tokens. It was published in September 2022. The catalogue files it under transcribe and translate. Three companies sell it. The cheapest is $0.0001 per Mtok in at Vercel AI Gateway.
Every current figure
- Maker
- OpenAI
- Register
- model
- Takes
- audio
- Returns
- text
- Context
- 448,000 tokens
- Longest answer
- 4,096 tokens
- Published
- September 2022
- Licence
- not read
- Sellers
- 3
- Price
- $0.0001 per Mtok in — Vercel AI Gateway
Known as 2 names
@cf/openai/whisperopenai/whisper-1