---
title: gpt-4, o1, and o4-mini Shut Down October 23, 2026
description: OpenAI's gpt-4, o1, and o4-mini model IDs stop responding on October 23, 2026. The exact deprecation notice, and how to migrate to GPT-5.6.
date: 2026-08-12T00:00:00.000Z
category: ai-productivity
tags: tokens, gpt, deprecation, openai
---

## Quick Answer

OpenAI's `gpt-4`, `gpt-4-0613`, `o1`, `o1-pro`, and `o4-mini` model IDs stop responding entirely on October 23, 2026, per OpenAI's own deprecations page. This is a hard cutover, not a warning: calls to these model IDs will error after that date. The named replacements are `gpt-5.6-sol` and `gpt-5.6-terra`.

## What's actually changing

This is the one figure in this series confirmed directly against a primary source, not paraphrased from third-party coverage. [OpenAI's own deprecations page](https://platform.openai.com/docs/deprecations) states its retirement policy in plain terms:

> "Unless safety or compliance concerns require a faster timeline, we provide the following minimum notice periods before model retirement: Generally available models: At least 6 months."

Under the "2026-04-22: Legacy GPT model snapshots" notice on that same page, `gpt-4`, `gpt-4-0613`, `o1`, `o1-pro`, and `o4-mini` are listed with a shutdown date of October 23, 2026, with `gpt-5.6-sol` and `gpt-5.6-terra` named as the direct replacements. That is roughly six months of notice from the 2026-04-22 posting date, consistent with OpenAI's own stated minimum.

## Structural Comparison Matrix

| Operational Aspect               | Before (until 2026-10-23) | After (2026-10-23 onward)        |
| :------------------------------- | :------------------------ | :------------------------------- |
| **`gpt-4` / `gpt-4-0613` calls** | Respond normally          | Return errors                    |
| **`o1` / `o1-pro` calls**        | Respond normally          | Return errors                    |
| **`o4-mini` calls**              | Respond normally          | Return errors                    |
| **Recommended model**            | Any of the above          | `gpt-5.6-sol` or `gpt-5.6-terra` |

## Fix it: migrate before the cutover, not after

A hard cutover means there is no graceful fallback once October 23, 2026 passes: a call to a retired model ID fails, full stop. The practical fix is a model-string swap to `gpt-5.6-sol` or `gpt-5.6-terra`, but treat that as the start of the migration, not the whole thing.

`gpt-5.6-sol` and `gpt-5.6-terra` use the `o200k_base` encoding, not the `cl100k_base` encoding the retiring models used, which changes token counts for identical prompts. See [GPT-5.6's Context Window](/ai-productivity/gpt-5-6-context-window-922k-tokens/) for what that means for chunking and cost estimation. GPT-5.6 also changed prompt-caching behavior, covered in [GPT-5.6 Ends Free Prompt-Cache Writes](/ai-productivity/gpt-5-6-prompt-cache-write-premium/), so a migration that only swaps the model string and skips re-checking caching configuration will get a real, avoidable cost surprise.

<Callout type="warning" title="Check your own numbers before the deadline">
  Use the free <a href="/tools/ai-token-counter/">AI Token Counter</a> to see
  how your actual prompts tokenize under the newer encoding before you migrate,
  not after, then run those counts through the{" "}
  <a href="/tools/llm-pricing-calculator/">LLM Pricing Calculator</a> to see
  what the migration actually costs against GPT-5.6's current rates.
</Callout>

## Confirmed version

Fetched directly from [OpenAI's own API deprecations page](https://developers.openai.com/api/docs/deprecations), notice dated 2026-04-22, shutdown date 2026-10-23. This is a primary source, not third-party reporting. Browse more coverage in the [AI Productivity](/ai-productivity) archive, or start from [The 2026 LLM Token & Pricing Reset](/ai-productivity/2026-llm-token-pricing-reset/) hub.