ModelRot

gpt-audio vs gpt-audio-1.5

OpenAI names gpt-audio-1.5 as the replacement for gpt-audio. gpt-audio shuts down on Jan 20, 2027. At standard list prices, gpt-audio-1.5 costs 0% per token (blended 3:1 input:output).

Deprecated→Active
Per 1M tokensgpt-audiogpt-audio-1.5
Input$2.50$2.50
Output$10$10
Blended change0%
ProviderOpenAIOpenAI
Statusdeprecatedactive
ShutdownJan 20, 2027—
Context window——

Migrating

  • Replace the ID gpt-audio with gpt-audio-1.5 everywhere it appears, including .env files, config and infrastructure templates.
  • Run your evaluation set or golden prompts on both before switching: output style, refusals and tool calling can differ between generations.
  • Check max output tokens and parameters: newer models sometimes rename or drop sampling options.
  • Watch the repo on ModelRot so the next retirement doesn't surprise you. gpt-audio-1.5 lifecycle.