Skip to content
modeldeprecations.dev
Calendar Changelog API GitHub

Providers

Alibaba Amazon Bedrock Anthropic Cohere DeepSeek Google MiniMax Mistral Moonshot AI OpenAI Vertex AI xAI Xiaomi MiMo Z.ai

Providers

Alibaba 26 Amazon Bedrock 8 Anthropic 31 Cohere 35 DeepSeek 5 Google 34 MiniMax 17 Mistral 53 Moonshot AI 18 OpenAI 106 Vertex AI 8 xAI 26 Xiaomi MiMo 4 Z.ai 22
Mistral mistral-medium-2505

Mistral Medium 3 (Mistral)

Retired

Yes — Mistral Medium 3 is retired. Mistral deprecated it on May 22, 2026 and shut it down on August 31, 2026; API requests to it now fail. The recommended replacement is Mistral Medium 3.5.

The model that reintroduced a middle tier to Mistral's API after two years of only Small and Large, and the first sign that Large was being quietly demoted. It shares its 31 August 2026 shutdown with Medium 3.1, so both generations of the id go dark on the same day rather than the older one leaving first.

The facts

Provider Mistral
Model id mistral-medium-2505
Released —
Deprecated May 22, 2026
Shutdown August 31, 2026 ·
Status Retired
Last verified August 3, 2026

What to use instead

Mistral Medium 3.5 mistral-medium-3-5-26-04 Provider-recommended Active

What parameters mistral-medium-3-5-26-04 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": "mistral-medium-2505"
+ "model": "mistral-medium-3-5-26-04"

Frequently asked questions

When did Mistral Medium 3 shut down?
Mistral Medium 3 shut down on August 31, 2026. API requests to it fail from that date onward.
What replaces Mistral Medium 3?
Mistral recommends Mistral Medium 3.5 (`mistral-medium-3-5-26-04`) as the replacement for Mistral Medium 3.
Is Mistral Medium 3 still available?
No. Mistral Medium 3 is retired and no longer served — it was shut down on August 31, 2026. Calls to it return an error.
How do I migrate from Mistral Medium 3 to mistral-medium-3-5-26-04?
Swap the model id in your API call: replace "mistral-medium-2505" with "mistral-medium-3-5-26-04". Keep the rest of the request the same, then re-check the parameters the new model accepts before you ship.

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:

[![mistral-medium-2505](https://img.shields.io/endpoint?url=https://modeldeprecations.dev/badge/mistral/mistral-medium-2505.json)](https://modeldeprecations.dev/mistral/mistral-medium-2505)

Other Mistral models

All Mistral 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.