Skip to content

Model detail

whisper

Provided by OpenAI
Pay-as-you-go

Model specs

Context length
Max output
I/O modalities
Released

02

API endpoints

One MixRoute gateway, OpenAI-compatible

  • OpenAI-compatible /v1/chat/completions POST

03

Pricing

Flat rate, unit: /1M Tokens

Input

$6.0000 /1M Tokens

Completion

$6.0000 /1M Tokens

05

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Open-source speech recognition across 50+ languages

Use Whisper for transcription and translation from audio files. It supports 50+ languages, accepts mp3/mp4/wav/webm formats up to 25 MB, and is priced per minute of audio.

What should you check before using it?

Consider GPT-4o Transcribe for improved accuracy

GPT-4o Transcribe offers better word error rate. Test your audio to compare Whisper vs GPT-4o Transcribe for your language and audio quality.

Why use it through MixRoute?

Use the compatible endpoint with stable model ID

Use the confirmed compatible endpoint with model ID whisper through MixRoute.

08

Token cost estimator

Live estimate from this page's pricing, not an actual bill

This model has no cache-read price; caching is not counted

09

FAQ

Whisper is OpenAI’s open-source automatic speech recognition model, available via API as whisper-1. It supports transcription and translation across 50+ languages from audio files up to 25 MB.

One endpoint, a testable decision

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.