Skip to content
modeldeprecations.dev
Calendar Changelog API GitHub

Providers

Anthropic Cohere DeepSeek Google MiniMax Mistral Moonshot AI OpenAI xAI Z.ai

Providers

Anthropic 29 Cohere 35 DeepSeek 5 Google 24 MiniMax 17 Mistral 53 Moonshot AI 18 OpenAI 103 xAI 26 Z.ai 22
DeepSeek deepseek-reasoner

DeepSeek Reasoner (DeepSeek)

Retired

Yes — DeepSeek Reasoner is retired. DeepSeek deprecated it on April 24, 2026 and shut it down on July 24, 2026; API requests to it now fail. The recommended replacement is DeepSeek V4 Flash.

The id that served DeepSeek-R1 in January 2025, the open-weights reasoning model that made chain-of-thought cheap and briefly moved the US stock market. It was the first mainstream API to hand back the reasoning trace itself in `reasoning_content`. From V3.1 onwards it stopped being a separate model and became the thinking half of a hybrid one, which is why V4 replaced it with a request parameter rather than another id.

The facts

Provider DeepSeek
Model id deepseek-reasoner
Released January 20, 2025
Deprecated April 24, 2026
Shutdown July 24, 2026 · 10 days ago
Status Retired
Last verified August 3, 2026

What to use instead

DeepSeek V4 Flash deepseek-v4-flash Provider-recommended Active

deepseek-reasoner routed to V4-Flash with thinking on, which is the default, so `model: "deepseek-v4-flash"` reproduces the old behaviour. Use `thinking.reasoning_effort` (`low`, `high`, `max`) to trade depth against cost, and deepseek-v4-pro for the hardest problems.

What parameters deepseek-v4-flash 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": "deepseek-reasoner"
+ "model": "deepseek-v4-flash"

Frequently asked questions

When did DeepSeek Reasoner shut down?
DeepSeek Reasoner shut down on July 24, 2026. API requests to it fail from that date onward.
What replaces DeepSeek Reasoner?
DeepSeek recommends DeepSeek V4 Flash (`deepseek-v4-flash`) as the replacement for DeepSeek Reasoner. deepseek-reasoner routed to V4-Flash with thinking on, which is the default, so `model: "deepseek-v4-flash"` reproduces the old behaviour. Use `thinking.reasoning_effort` (`low`, `high`, `max`) to trade depth against cost, and deepseek-v4-pro for the hardest problems.
Is DeepSeek Reasoner still available?
No. DeepSeek Reasoner is retired and no longer served — it was shut down on July 24, 2026. Calls to it return an error.
How do I migrate from DeepSeek Reasoner to deepseek-v4-flash?
Swap the model id in your API call: replace "deepseek-reasoner" with "deepseek-v4-flash". deepseek-reasoner routed to V4-Flash with thinking on, which is the default, so `model: "deepseek-v4-flash"` reproduces the old behaviour. Use `thinking.reasoning_effort` (`low`, `high`, `max`) to trade depth against cost, and deepseek-v4-pro for the hardest problems.

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:

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

Other DeepSeek models

All DeepSeek 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.