ModelRot
Deprecatedgpt-audio

gpt-audio

gpt-audio deprecation date: Jan 20, 2027, replacement gpt-audio-1.5.

Countdown

64 days

Jan 20, 2027

Replacement

gpt-audio-1.5

Blended price 0%

Price per 1M tokens

$2.50 in · $10 out

Standard tier, list price

Price comparison

Per 1M tokensgpt-audiogpt-audio-1.5
Input$2.50$2.50
Output$10$10
Blended change0%

Full migration notes: gpt-audio vs gpt-audio-1.5

Timeline

  1. Deprecation announced

    Jul 20, 2026

  2. Shutdown

    Jan 20, 2027

Source: https://developers.openai.com/api/docs/deprecations · checked Nov 16, 2026

Change history

Related OpenAI models

FAQ

When does gpt-audio shut down?

OpenAI lists Jan 20, 2027 as the shutdown date for gpt-audio (64 days from today). After that date, API calls to it fail.

What should I replace gpt-audio with?

OpenAI recommends gpt-audio-1.5. At list prices that is a 0% change in blended cost per token.

How much does gpt-audio cost per 1M tokens?

$2.50 per 1M input tokens and $10 per 1M output tokens at the standard tier, from OpenAI's pricing page.

How do I find every place my code calls gpt-audio?

Paste your code or a public GitHub repo URL into ModelRot's free scanner. It lists every file and line that uses gpt-audio or any other retiring model, with the replacement and cost change.