ModelClock
ONE MODEL, EVERY PLATFORM

gpt-5.4-nano deprecation and shutdown dates on every platform

gpt-5.4-nano is tracked on 5 providers and hosting routes. First to go: Perplexity Agent shuts down openai/gpt-5.4-nano on Oct 24, 2026. 2 other routes have a later published date.

Last updated

Perplexity Agent

gpt-5.4-nano on Perplexity Agent
DateModelStatusReplacementSource
openai/gpt-5.4-nanoShuts downTomorrowNone publishedNotice ↗

OpenAI

gpt-5.4-nano on OpenAI
DateModelStatusReplacementSource
gpt-5.4-nanoShuts down160 daysgpt-6-lunaNotice ↗

AzureMicrosoft Azure / Foundry

gpt-5.4-nano on Azure
DateModelStatusReplacementSource
gpt-5.4-nano (2026-03-17)Shuts down333 daysNone publishedNotice ↗

ElevenLabs

gpt-5.4-nano on ElevenLabs
DateModelStatusReplacementSource
—gpt-5.4-nanoNo deprecation notice trackedNone publishedNotice ↗
—gpt-5.4-nano-2026-03-17No deprecation notice trackedNone publishedNotice ↗

Deepgram

gpt-5.4-nano on Deepgram
DateModelStatusReplacementSource
—gpt-5.4-nanoNo deprecation notice trackedNone publishedNotice ↗

Every provider sets its own dates

A deadline on one platform says nothing about another: OpenAI, Azure, Amazon Bedrock, Google Vertex AI and model routers each retire their own copies on their own schedule. Snapshots of the same model (for example dated versions) are listed separately because each has its own date. Rows marked “No deprecation notice tracked” mean ModelClock has not seen a retirement notice for that route, not that one cannot exist.