Skip to content
modeldeprecations.dev
Calendar Changelog API GitHub

Providers

Anthropic Google OpenAI

Providers

Anthropic 29 Google 24 OpenAI 103
OpenAI gpt-4o-realtime-preview

GPT-4o Realtime preview (OpenAI)

Retired

Yes — GPT-4o Realtime preview is retired. OpenAI deprecated it on September 15, 2025 and shut it down on May 7, 2026; API requests to it now fail. The recommended replacement is GPT Realtime 1.5.

The model that introduced speech-to-speech over a WebSocket, with interruption handling and sub-second response — the first time a voice agent could be built without stitching together transcription, a chat model and text-to-speech. It stayed a preview for its entire eighteen-month life.

The facts

Provider OpenAI
Model id gpt-4o-realtime-preview
Also published as gpt-4o-realtime-preview-2025-06-03, gpt-4o-realtime-preview-2024-12-17
Released October 1, 2024
Deprecated September 15, 2025
Shutdown May 7, 2026 · 84 days ago
Status Retired
Last verified July 30, 2026

What to use instead

OpenAI GPT Realtime 1.5 gpt-realtime-1.5 Provider-recommended Active

The session event schema changed between preview and GA. Expect to update event handlers, not just the model id.

What parameters gpt-realtime-1.5 accepts on modelparams.dev

Change the id

In most cases the migration is one string. Check the parameter differences before you ship — newer models drop older sampling knobs more often than they add them. 

- "model": "gpt-4o-realtime-preview"
+ "model": "gpt-realtime-1.5"

Frequently asked questions

When did OpenAI GPT-4o Realtime preview shut down?
OpenAI GPT-4o Realtime preview shut down on May 7, 2026. API requests to it fail from that date onward.
What replaces OpenAI GPT-4o Realtime preview?
OpenAI recommends GPT Realtime 1.5 (`gpt-realtime-1.5`) as the replacement for OpenAI GPT-4o Realtime preview. The session event schema changed between preview and GA. Expect to update event handlers, not just the model id.
Is OpenAI GPT-4o Realtime preview still available?
No. OpenAI GPT-4o Realtime preview is retired and no longer served — it was shut down on May 7, 2026. Calls to it return an error.
How do I migrate from OpenAI GPT-4o Realtime preview to gpt-realtime-1.5?
Swap the model id in your API call: replace "gpt-4o-realtime-preview" with "gpt-realtime-1.5". The session event schema changed between preview and GA. Expect to update event handlers, not just the model id.
Does this apply to gpt-4o-realtime-preview-2025-06-03 too?
Yes. OpenAI GPT-4o Realtime preview is also published as `gpt-4o-realtime-preview-2025-06-03`, `gpt-4o-realtime-preview-2024-12-17`; those ids share the same lifecycle dates as `gpt-4o-realtime-preview`.

Sources

Found something wrong? The data is one YAML file — edit it on GitHub.

This page, for machines

JSON Markdown Badge JSON

Drop the badge in a README so it turns red the day this model is retired:

[![gpt-4o-realtime-preview](https://img.shields.io/endpoint?url=https://modeldeprecations.dev/badge/openai/gpt-4o-realtime-preview.json)](https://modeldeprecations.dev/openai/gpt-4o-realtime-preview)

Other OpenAI models

All OpenAI deprecations →

How to use this site

The full guide, in Markdown. Copy it and hand it to a coding agent verbatim.

# How to use modeldeprecations.dev

[modeldeprecations.dev](https://modeldeprecations.dev) answers one question per model: is it deprecated,
when does it shut down, and what replaces it. Every date on the site is cited to the
provider's own documentation, with the date we last checked it.

Three lifecycle states are used, matching the providers' own vocabulary:

- **active** — still supported, no deprecation announced.
- **deprecated** — the provider has announced it is going away. It still answers requests.
- **retired** — API access is gone. Requests fail.

A model can be active *and* carry a shutdown date: Anthropic publishes a
"not sooner than" date and Google publishes an earliest shutdown date for models
that are current and fully supported. Those are reported as scheduled shutdowns,
not deprecations, because that is what the provider actually committed to.

## Check one model

```bash
curl https://modeldeprecations.dev/api/v1/models/openai/gpt-4-32k.json
```

Or fetch the page as Markdown, which includes the answer, the dates and the sources:

```bash
curl https://modeldeprecations.dev/openai/gpt-4-32k.md
```

## Full catalog

```bash
curl https://modeldeprecations.dev/api/v1/models.json
```

Ids are `provider/model`. Dated snapshots (`gpt-4-32k-0613`) are listed as aliases of
their canonical entry rather than as separate records.

Each entry carries `computed_status`, the lifecycle state recomputed against the build
date — so a model whose shutdown has passed reads `retired` without anyone editing data.

## Badges

A shields.io endpoint per model, for READMEs that should go red when a model dies:

```
https://img.shields.io/endpoint?url=https://modeldeprecations.dev/badge/openai/gpt-4-32k.json
```

## Calendar and changelog

- Subscribe to every shutdown date: https://modeldeprecations.dev/calendar.ics
- Changelog RSS: https://modeldeprecations.dev/changelog.xml

## JSON Schema

```bash
curl https://modeldeprecations.dev/api/v1/schema.json
```

## Contribute

Data lives in YAML under `models/{provider}/{model}.yaml` in the
[GitHub repo](https://github.com/mnfst/modeldeprecations.dev). Every lifecycle date needs a source URL; CI rejects a
date without one. Open a PR.

## For agents

- Machine-readable overview: https://modeldeprecations.dev/llms.txt
- This guide plus every model inline: https://modeldeprecations.dev/llms-full.txt
- Any page also exists as Markdown: append `.md` to a model URL.
- In a browser, this site registers a **WebMCP** tool on `navigator.modelContext`:
  `check_model_deprecation`, `list_shutdowns`, `find_replacement`, and `get_usage_guide`.
- Parameters each model accepts are catalogued on the sibling site, https://modelparams.dev.