Skip to content

Model detail

whisper-1

Provided by OpenAI
Pay-as-you-go

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. Accepts formats including mp3, mp4, wav, and webm. Priced per minute of audio duration, billed to the nearest second.

Model specs

Context length
Max output
I/O modalities
Audio
Released
2026-04

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?

Start with the documented use cases for whisper-1

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. Accepts formats including mp3, mp4, wav, and webm. Priced per minute of audio duration, billed to the nearest second.

What should you check before using it?

Validate limits, pricing, and a representative workload

Review the current model limits and pricing record before production use.

How do you call it through MixRoute?

Use the documented endpoint and exact model ID

The model record lists OpenAI-compatible access via POST /v1/chat/completions with model ID whisper-1.

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. Accepts formats including mp3, mp4, wav, and webm. Priced per minute of audio duration, billed to the nearest second.

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.