Skip to content
modeldeprecations.dev

o3 (OpenAI)

Deprecated Shuts down in 134 days

Yes — OpenAI deprecated o3 on June 11, 2026 and shuts it down on December 11, 2026 (in 134 days). The recommended replacement is GPT-5.6 Sol.

The reasoning model that made chain-of-thought a product feature rather than a prompting trick, and the last o-series flagship before the line was folded into GPT-5. It outlived o1 by more than a year and is still widely referenced in evaluation code and papers.

The facts

Provider OpenAI
Model id o3
Also published as o3-2025-04-16
Released April 16, 2025
Deprecated June 11, 2026
Shutdown December 11, 2026 · in 134 days
Status Deprecated
Last verified July 30, 2026

What to use instead

OpenAI GPT-5.6 Sol gpt-5.6-sol Provider-recommended Active

Both are reasoning models, so max_completion_tokens and reasoning_effort carry over. Reasoning tokens are billed as output on both, which is the line item to compare.

What parameters gpt-5.6-sol 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": "o3"
+ "model": "gpt-5.6-sol"

Frequently asked questions

When will OpenAI o3 shut down?
OpenAI o3 is scheduled to shut down on December 11, 2026, in 134 days.
What replaces OpenAI o3?
OpenAI recommends GPT-5.6 Sol (`gpt-5.6-sol`) as the replacement for OpenAI o3. Both are reasoning models, so max_completion_tokens and reasoning_effort carry over. Reasoning tokens are billed as output on both, which is the line item to compare.
Is OpenAI o3 still available?
Yes, for now. OpenAI o3 is deprecated but still answers requests until December 11, 2026. Deprecated models get no further updates and are the first to lose capacity.
How do I migrate from OpenAI o3 to gpt-5.6-sol?
Swap the model id in your API call: replace "o3" with "gpt-5.6-sol". Both are reasoning models, so max_completion_tokens and reasoning_effort carry over. Reasoning tokens are billed as output on both, which is the line item to compare.
Does this apply to o3-2025-04-16 too?
Yes. OpenAI o3 is also published as `o3-2025-04-16`; that id shares the same lifecycle dates as `o3`.

Models that migrate here

OpenAI names o3 as the replacement for one model.

Sources

Found something wrong? The data is one YAML file — edit it on GitHub.

This page, for machines

Drop the badge in a README so it turns red the day this model is retired:

[![o3](https://img.shields.io/endpoint?url=https://modeldeprecations.dev/badge/openai/o3.json)](https://modeldeprecations.dev/openai/o3)

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.