Skip to content
modeldeprecations.dev

Amazon deprecated models

Every Amazon model we track, split by where it is in its life: what is shutting down and when, what has already gone, and what is still safe to build on. 8 models, current as of August 3, 2026.

Shutting down

Announced shutdown dates, soonest first. These still answer requests until the date lands.

Model Status Shutdown Replacement
Amazon Nova Premier
nova-premier
Deprecated September 14, 2026
in 42 days
nova-pro
Amazon Nova Sonic
nova-sonic
Deprecated September 14, 2026
in 42 days
gpt-realtime-2.1
Amazon Nova Canvas
nova-canvas
Deprecated September 30, 2026
in 58 days
imagen-4.0-generate-001
Amazon Nova Reel v1.0
nova-reel-1-0
Deprecated September 30, 2026
in 58 days
MiniMax-H3
Amazon Nova Reel v1.1
nova-reel-1-1
Deprecated September 30, 2026
in 58 days
MiniMax-H3

Active

No deprecation and no shutdown date announced as of the last check.

Model Status Shutdown Replacement
Amazon Nova Lite
nova-lite
Active
Amazon Nova Micro
nova-micro
Active
Amazon Nova Pro
nova-pro
Active

Keep up with Amazon deprecations

Shutdown dates land with months of notice and then arrive all at once. Subscribe to the calendar and they show up alongside everything else you plan around.

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.