---
id: "openai/whisper-1"
also: ["openai/whisper-1", "vercel/openai/whisper-1"]
card_usd_per_m: "100.0 in, 0.0 out, at openai"
cheapest_list_usd_per_m: "0.0001 in, 0.0 out, at openai on vercel"
cheapest_effective_usd_per_m: "0.0001 in, 0.0 out, at openai on vercel"
context: 0
max_output: 0
input: ["audio"]
output: ["transcription"]
released: "2026-04-27"
api: ["/api/v1/audio/transcriptions"]
params: ["max_tokens", "stop", "temperature"]
endpoints: 2
gateways: "openrouter (1), vercel (1)"
no_training: 2
trains: 0
retains_prompts: 2
---
# OpenAI: Whisper 1

Whisper is a general-purpose speech recognition model, trained on a large dataset of diverse audio. You can also use it as a multitask model to perform multilingual speech recognition as well as speech translation and language identification.