Skip to content
OpenAI

GPT Audio Mini

GPT Audio Mini is a multimodal model made by OpenAI, added to the catalog on 19 Jan 2026. It has a context window of 128,000 tokens and costs $0.60 per 1M input tokens and $2.40 per 1M output tokens. It accepts text and audio and produces text and audio. Typical uses: create engaging audio content from text, transcribe audio into accurate text and develop applications for voice assistants.

Price checked ยท source: OpenRouter

What GPT Audio Mini is

OpenAI's GPT Audio Mini, launched on January 19, 2026, is designed for both text and audio processing. With a substantial context length of 128,000 tokens, this model efficiently handles various input modalities including text and audio, producing output in the same formats. It features an upgraded decoder that enhances voice quality, ensuring more natural-sounding results and improved voice consistency. This model is ideal for applications that require seamless integration of audio and text, making it a versatile tool for developers and content creators alike.

Key features

  • Upgraded decoder for natural-sounding voices
  • Handles both text and audio inputs
  • Supports a large context length of 128,000 tokens
  • Maintains better voice consistency
  • Flexible output in text and audio formats

Typical uses

  • Create engaging audio content from text
  • Transcribe audio into accurate text
  • Develop applications for voice assistants
  • Enhance multimedia presentations with voice
  • Generate audio responses for chatbots

GPT Audio Mini pricing

US dollars, list price through OpenRouter.

Checked
GPT Audio Mini price list
ItemStandard
Input, per 1M tokens$0.60
Output, per 1M tokens$2.40

No price change since it was added on 19 Jan 2026.

What typical tasks cost with GPT Audio Mini
What a task costsCost
Answer a short question500 in / 300 out$0.0010
Summarise a 50-page PDF25,000 in / 800 out$0.017
Review a 2,000-line source file30,000 in / 2,000 out$0.023
Read a 300-page contract set150,000 in / 1,500 out$0.094
Check the provider's pageToken counts are estimates. A maker's direct price and its monthly plans can differ from the per-token price shown here.

GPT Audio Mini specifications

GPT Audio Mini limits and identity
Model idopenai/gpt-audio-mini
Versiongpt-audio-mini
Context window128,000 tokensAbout 96,000 English words
Max output16,384 tokens
Knowledge cutoffNot published
Added to catalog19 Jan 2026
GPT Audio Mini capabilities
Input typestext, audio
Output typestext, audio
Tool callingYes
Structured outputsYes
Reasoning effort controlNo
Content moderationApplied by provider

Sample outputs

The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.

No output has been recorded for GPT Audio Mini yet.

GPT Audio Mini questions

How much does GPT Audio Mini cost?

GPT Audio Mini costs $0.60 per 1M input tokens and $2.40 per 1M output tokens through OpenRouter, as checked on 22 Nov 2026. Summarising a 50-page PDF costs about $0.017.

What is the context window of GPT Audio Mini?

128,000 tokens, or roughly 96,000 English words. It can write up to 16,384 tokens in one response.

Can GPT Audio Mini read images and PDFs?

No. It accepts text and audio only. It produces text and audio, so it cannot generate images.

How do I try GPT Audio Mini?

Use the "Try GPT Audio Mini" button on this page. It opens the chat with GPT Audio Mini selected; you type the question and press send.

Try GPT Audio Mini on your own question.

It opens in the chat with this model already selected.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.