GPT-4o mini Transcribe
A speech-to-text model that uses GPT-4o Mini to transcribe audio, improving word error rate and language recognition accuracy over the original Whisper models.
audio → text · made by OpenAI
$1.25→$5per Mtok in / out
Microsoft Azure AI · 2 sellers
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| Microsoft Azure AI cloud | standard | $1.25per Mtok in$5per Mtok out$3per Mtok in, audioraw.githubusercontent.com · read 2026-10-31 |
| Vercel AI Gateway aggregator | standard | $1.25per Mtok in$5per Mtok outai-gateway.vercel.sh · read 2026-08-25 |
About
GPT-4o mini Transcribe — a text model from OpenAI, sold by 2 companies from $1.25 in and $5 out per million tokens.
It takes audio and returns text, with a context window of 16,000 tokens. It was published in March 2025, trained on material up to June 2024. The catalogue files it under transcribe. Two companies sell it. The cheapest is $1.25 in and $5 out per million tokens at Microsoft Azure AI.
Every current figure
- Maker
- OpenAI
- Register
- model
- Takes
- audio
- Returns
- text
- Context
- 16,000 tokens
- Published
- March 2025
- Knowledge to
- June 2024
- Licence
- not read
- Sellers
- 2
- Maker's own price
- not read
- Price
- $1.25 in and $5 out per million tokens — Microsoft Azure AI
Known as 2 names
gpt4o mn trscb 1215openai/gpt-4o-mini-transcribe