OpenAI
MultimodalAUTO PROFILEPriced via OpenRouter

GPT Audio Mini

text+audio->text+audio

GPT Audio Mini is an audio model: speech-to-text, text-to-speech, or a unified audio-in/audio-out variant depending on the provider. Available via OpenAI. 128,000-token context. Mid-tier pricing.

GPT Audio Mini is a multimodal AI model from OpenAI. It costs $0.6000 per million input tokens and $2.40 per million output tokens (blended $1.14/M), with a 128,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.6000/M
per million input tokens
OUTPUT
$2.40/M
per million output tokens
BLENDED 70/30
$1.14/M
unchanged since 3 May
CONTEXT
128,000
tokens

From OpenRouter's listing, read on 17 Nov 2026.

What it is good at
  • Speech transcription
  • Multilingual coverage
  • Realtime or batch ingest depending on provider
  • Multimodal: handles images alongside text
Typical use cases
  • Meeting transcription
  • Voice interfaces
  • Subtitle pipelines

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from OpenAI

See all 28 →

Frequently asked questions

How much does GPT Audio Mini cost?

GPT Audio Mini costs $0.6000 per million input tokens and $2.40 per million output tokens, for a blended reference rate of $1.14 per million tokens.

What is GPT Audio Mini's context window?

GPT Audio Mini supports up to 128,000 tokens of context in a single request.

What is GPT Audio Mini best for?

GPT Audio Mini is well suited to Speech transcription, Multilingual coverage and Realtime or batch ingest depending on provider.

Who makes GPT Audio Mini?

GPT Audio Mini is developed and served by OpenAI.

Terms used on this page