Skip to content
modeldeprecations.dev
Calendar Changelog API GitHub

Providers

Anthropic Google OpenAI

Providers

Anthropic 29 Google 24 OpenAI 103
OpenAI gpt-realtime-mini

GPT Realtime mini (OpenAI)

Deprecated Shuts down in 174 days

Yes — OpenAI deprecated GPT Realtime mini on July 20, 2026 and shuts it down on January 20, 2027 (in 174 days). The recommended replacement is GPT Realtime 2.1 mini.

The cost tier of the first GA realtime generation, and the successor to gpt-4o-mini-realtime-preview. It was deprecated in July 2026, which puts anyone who migrated off the preview on their second voice migration in a year.

The facts

Provider OpenAI
Model id gpt-realtime-mini
Released —
Deprecated July 20, 2026
Shutdown January 20, 2027 · in 174 days
Status Deprecated
Last verified July 30, 2026

What to use instead

OpenAI GPT Realtime 2.1 mini gpt-realtime-2.1-mini Provider-recommended Active

A same-family upgrade, so session events should carry over more cleanly than the preview-to-GA move did.

What parameters gpt-realtime-2.1-mini 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-realtime-mini"
+ "model": "gpt-realtime-2.1-mini"

Frequently asked questions

When will OpenAI GPT Realtime mini shut down?
OpenAI GPT Realtime mini is scheduled to shut down on January 20, 2027, in 174 days.
What replaces OpenAI GPT Realtime mini?
OpenAI recommends GPT Realtime 2.1 mini (`gpt-realtime-2.1-mini`) as the replacement for OpenAI GPT Realtime mini. A same-family upgrade, so session events should carry over more cleanly than the preview-to-GA move did.
Is OpenAI GPT Realtime mini still available?
Yes, for now. OpenAI GPT Realtime mini is deprecated but still answers requests until January 20, 2027. Deprecated models get no further updates and are the first to lose capacity.
How do I migrate from OpenAI GPT Realtime mini to gpt-realtime-2.1-mini?
Swap the model id in your API call: replace "gpt-realtime-mini" with "gpt-realtime-2.1-mini". A same-family upgrade, so session events should carry over more cleanly than the preview-to-GA move did.

Models that migrate here

OpenAI names GPT Realtime mini as the replacement for one model.

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-realtime-mini](https://img.shields.io/endpoint?url=https://modeldeprecations.dev/badge/openai/gpt-realtime-mini.json)](https://modeldeprecations.dev/openai/gpt-realtime-mini)

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.