Skip to content
modeldeprecations.dev
Calendar Changelog API GitHub

Providers

Anthropic Google OpenAI

Providers

Anthropic 29 Google 24 OpenAI 103
OpenAI babbage-002

babbage-002 (OpenAI)

Deprecated Shuts down in 60 days

Yes — OpenAI deprecated babbage-002 on September 26, 2025 and shuts it down on September 28, 2026 (in 60 days). The recommended replacement is GPT-5.4 mini.

A base completions model kept in service almost entirely as a fine-tuning target for classification work, where a small model trained on your own labels still beat prompting a large one. Its September 2026 shutdown ends that option.

The facts

Provider OpenAI
Model id babbage-002
Released August 22, 2023
Deprecated September 26, 2025
Shutdown September 28, 2026 · in 60 days
Status Deprecated
Last verified July 30, 2026

What to use instead

OpenAI GPT-5.4 mini gpt-5.4-mini Provider-recommended Active

Existing fine-tunes do not transfer. Budget for re-running training on the new base and re-validating accuracy — a base-model fine-tune and an instruction-model fine-tune do not behave the same way.

What parameters gpt-5.4-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": "babbage-002"
+ "model": "gpt-5.4-mini"

Frequently asked questions

When will OpenAI babbage-002 shut down?
OpenAI babbage-002 is scheduled to shut down on September 28, 2026, in 60 days.
What replaces OpenAI babbage-002?
OpenAI recommends GPT-5.4 mini (`gpt-5.4-mini`) as the replacement for OpenAI babbage-002. Existing fine-tunes do not transfer. Budget for re-running training on the new base and re-validating accuracy — a base-model fine-tune and an instruction-model fine-tune do not behave the same way.
Is OpenAI babbage-002 still available?
Yes, for now. OpenAI babbage-002 is deprecated but still answers requests until September 28, 2026. Deprecated models get no further updates and are the first to lose capacity.
How do I migrate from OpenAI babbage-002 to gpt-5.4-mini?
Swap the model id in your API call: replace "babbage-002" with "gpt-5.4-mini". Existing fine-tunes do not transfer. Budget for re-running training on the new base and re-validating accuracy — a base-model fine-tune and an instruction-model fine-tune do not behave the same way.

Models that migrate here

OpenAI names babbage-002 as the replacement for 2 models.

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:

[![babbage-002](https://img.shields.io/endpoint?url=https://modeldeprecations.dev/badge/openai/babbage-002.json)](https://modeldeprecations.dev/openai/babbage-002)

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.