gpt-4o-audio-preview — Retired

Quick fix — copy & paste

Choose your language. The "before" block matches the deprecated call; the "after" block is the drop-in replacement.

# OpenAI: gpt-4o-audio-preview (deprecated)
model = "gpt-4o-audio-preview"

# Replacement
model = "gpt-audio-1.5"

// OpenAI: gpt-4o-audio-preview (deprecated)
const model = "gpt-4o-audio-preview";

// Replacement
const model = "gpt-audio-1.5";

"model": "gpt-4o-audio-preview"

"model": "gpt-audio-1.5"

This migration was generated automatically from the model rename. If your code does more than swap a model id, double-check request/response shapes against the official OpenAI migration guide.

Error messages

Seeing one of these? You're in the right place.

• model_not_found: gpt-4o-audio-preview
• The model `gpt-4o-audio-preview` has been deprecated
• The model `gpt-4o-audio-preview` does not exist or you do not have access to it

Replacement options

• gpt-audio-1.5 Compare token cost →

Other OpenAI deprecations

• dall-e-2 2026-05-12 · 4d
• dall-e-3 2026-05-12 · 4d
• computer-use-preview 2026-07-23 · 76d
• gpt-4o-audio-preview-2024-12-17 2026-07-23 · 76d
• gpt-4o-mini-audio-preview-2024-12-17 2026-07-23 · 76d

What this means for your code

gpt-4o-audio-preview is an audio model used for either speech input or speech output. Audio models have separate pricing for input audio (per minute) and output audio (per minute or per character). Replacements may change voice list, audio format support, or sample rate.

gpt-4o-audio-preview was retired by OpenAI on 2026-05-07. API calls now return an error and the model is no longer accessible. New code should use gpt-audio-1.5; legacy code that still references this model id needs to be updated immediately.

Find every call in your codebase

Before you change anything, locate every place the deprecated model id is referenced. Search source files, environment files, feature flags, and config repos. Use these commands from your project root:

grep -rn '"gpt-4o-audio-preview"' --include="*.py" .

grep -rn '"gpt-4o-audio-preview"' --include="*.{js,ts,tsx,jsx}" .

grep -rn "gpt-4o-audio-preview" .

Migration checklist

Steps in order. Skip any that don't apply, but read the whole list — for audio models, the non-obvious steps are usually the ones that break in production.

1. 1. Update the model id in audio API calls
2. 2. Verify the new model supports your audio format (mp3, wav, opus, flac)
3. 3. Map old voice ids to the new model's voice catalog
4. 4. Test with your longest and shortest audio inputs
5. 5. Recompute per-minute audio cost — input and output are usually priced separately