Skip to content
modeldeprecations.dev
Calendar Changelog API GitHub

Providers

Anthropic Google OpenAI

Providers

Anthropic 29 Google 24 OpenAI 103
OpenAI davinci

davinci (OpenAI)

Retired

Yes — davinci is retired. OpenAI deprecated it on July 6, 2023 and shut it down on January 4, 2024; API requests to it now fail. The recommended replacement is davinci-002.

The largest GPT-3 base model, and the one the 2020 paper actually described. It had no instruction tuning at all — you steered it with few-shot examples, which is the technique the whole prompt-engineering field grew out of. Retired January 2024.

The facts

Provider OpenAI
Model id davinci
Released June 11, 2020
Deprecated July 6, 2023
Shutdown January 4, 2024 · 938 days ago
Status Retired
Last verified July 30, 2026

What to use instead

OpenAI davinci-002 davinci-002 Provider-recommended Deprecated

davinci-002 was the named replacement base model and is itself deprecated, shutting down September 2026 — after which OpenAI hosts no base models at all.

What parameters davinci-002 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": "davinci"
+ "model": "davinci-002"

Where the migration path ends

The recommended successor has itself been replaced. Following the chain to a model that is still active today:

  1. davinci
  2. davinci-002 Deprecated
  3. gpt-5.4-mini Active

Frequently asked questions

When did OpenAI davinci shut down?
OpenAI davinci shut down on January 4, 2024. API requests to it fail from that date onward.
What replaces OpenAI davinci?
OpenAI recommends davinci-002 (`davinci-002`) as the replacement for OpenAI davinci. davinci-002 was the named replacement base model and is itself deprecated, shutting down September 2026 — after which OpenAI hosts no base models at all.
Is OpenAI davinci still available?
No. OpenAI davinci is retired and no longer served — it was shut down on January 4, 2024. Calls to it return an error.
How do I migrate from OpenAI davinci to davinci-002?
Swap the model id in your API call: replace "davinci" with "davinci-002". davinci-002 was the named replacement base model and is itself deprecated, shutting down September 2026 — after which OpenAI hosts no base models at all.

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:

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

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.