# OpenAI Model Shutdown Scanner (n8n, Make, code, GitHub repos) (`fifty50labs/openai-deprecation-scanner`) Actor

Free scan of n8n/Make workflow JSON, code, .env or a public GitHub repo for OpenAI models, endpoints and features that are shutting down (gpt-4o, o3, gpt-5, tts-1, whisper-1, Assistants, Agent Builder, /v1/prompts). Each hit: location, shutdown date, days left, replacement.

- **URL**: https://apify.com/fifty50labs/openai-deprecation-scanner.md
- **Developed by:** [Fifty50 Labs](https://apify.com/fifty50labs) (community)
- **Categories:** Developer tools, AI, Automation
- **Features:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-usage

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## OpenAI Model Shutdown Scanner

Find every OpenAI model, endpoint and feature in your automations and code that OpenAI is shutting down, with the date it stops working, the days you have left and what to switch to. Free to run.

Paste an **n8n workflow export, a Make blueprint, a code file or a `.env`**, or give a **public GitHub repo URL**. Results point to the exact place: the n8n node and field, the Make module, or the file and line.

### Use it for

- Checking whether an n8n / Make / Zapier-style workflow still calls `gpt-4o`, `gpt-4o-mini`, `o3`, `gpt-5`, `tts-1`, `whisper-1` or another retiring model.
- Auditing a repo before a shutdown wave: model IDs, dated snapshots (`gpt-4o-2024-08-06`), fine-tunes (`ft:gpt-4o-mini-2024-07-18:org::id`), realtime/audio/transcribe models, image models.
- Finding retiring features: reusable prompts (`/v1/prompts`, `pmpt_…`), Agent Builder workflows (`wf_…`), the Evals API, the Assistants API (`asst_…`, `beta.threads`, n8n Assistant nodes), fine-tuning job creation, `/v1/audio/translations`.
- AI agents that need a fast, deterministic answer to "will this break, when, and what replaces it?"

### Not for

- Fixing the code. It reports; it does not edit your workflow.
- Models from other providers (Anthropic, Google, Mistral) or Azure deployment names that hide the model ID behind a custom name.
- Private repos (paste the files instead) or models chosen at runtime from a database or API response.
- Prose mentions in your docs are reported too; check the `snippet` before acting on them.

### Important: bare aliases die too

`gpt-4o`, `gpt-4o-mini`, `gpt-4.1` and `gpt-4.1-mini` have no date in them, but they resolve to dated snapshots that shut down on **14 Jan 2027**. The scanner flags them and says so.

### Input

| Field | What it is |
|---|---|
| `text` | Pasted workflow JSON, code, `.env` or any text. JSON is parsed, so hits carry the node and field path. |
| `textName` | Optional file name shown in results. |
| `githubRepoUrl` | `https://github.com/owner/repo` or `…/tree/branch`. Skips `node_modules`, lock files, binaries and files over 1 MB; up to 4,000 files. |
| `githubRef` | Optional branch, tag or commit. |
| `includeAlreadyShutDown` | Default `true`: also report models already past their shutdown (these calls fail today). |

Example:

```json
{ "githubRepoUrl": "https://github.com/owner/repo" }
```

### Output

One dataset row per reference, sorted by shutdown date, then a final `summary` row.

```json
{
  "type": "finding",
  "kind": "model",
  "reference": "gpt-4o-mini",
  "file": "lead-bot.json",
  "node": "OpenAI Chat Model (@n8n/n8n-nodes-langchain.lmChatOpenAi)",
  "jsonPath": "nodes[1].parameters.model.value",
  "shutdownDate": "2027-01-14",
  "daysLeft": 61,
  "status": "deprecated",
  "replacement": "gpt-6-luna",
  "note": "Bare alias: it resolves to a dated snapshot that shuts down on this date…",
  "source": "https://platform.openai.com/docs/deprecations"
}
```

Code hits carry `line` and `snippet` in place of `node` / `jsonPath`. `daysLeft` of 0 or less means the model is already shut down. A Markdown table of the same results is saved in the key-value store as `REPORT`.

### Shutdown dates covered

Source: [OpenAI deprecations page](https://platform.openai.com/docs/deprecations), verified 14 Nov 2026.

| Shutdown | What | Replacement |
|---|---|---|
| 30 Nov 2026 | Agent Builder, Evals API/graders, `/v1/prompts` | Agents SDK / Workspace Agents; Promptfoo; prompts in your code |
| 1 Dec 2026 | `gpt-image-1.5`, `gpt-image-1-mini`, `chatgpt-image-latest` | `gpt-image-2.6-sunburst` / `-flare` |
| 11 Dec 2026 | `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5-pro`, `o3`, `o3-pro` | `gpt-6.1-sol`, `gpt-6.1-terra`, `gpt-6-luna` |
| 6 Jan 2027 | `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`; fine-tuning job creation | `gpt-realtime-2.1-mini` |
| 14 Jan 2027 | `gpt-4o` and `gpt-4o-mini` snapshots, `gpt-4.1`, `gpt-4.1-mini` (and their fine-tunes) | `gpt-6-luna` |
| 20 Jan 2027 | `gpt-realtime`, `gpt-audio`, `gpt-4o-realtime`, `gpt-4o-audio`, mini variants | `gpt-realtime-2.1`, `gpt-audio-1.5` |
| 10 Feb 2027 | `gpt-image-2` | `gpt-image-2.6-sunburst` / `-flare` |
| 26 Feb 2027 | `whisper-1`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, `/v1/audio/translations` | `gpt-live-transcribe` / `gpt-transcribe` |
| 1 Apr 2027 | `gpt-5.1`, `gpt-5.3-codex`, `gpt-5.4-nano` | `gpt-6-sol`, `gpt-6-luna` |

Already shut down and still reported: `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, `o1`, `o3-mini`, `o4-mini`, `gpt-4.1-nano`, `gpt-image-1`, `dall-e-2/3`, preview realtime/audio models, the Assistants API and others.

### Pricing

Free. You pay only Apify platform usage, typically a fraction of a cent per scan.

### Limits

- Matching is exact and case-sensitive on model IDs, so `GPT-4o` written in prose is not flagged; `gpt-4o` in code or config is.
- The `o3` pattern can match an unrelated standalone token named `o3`; check the snippet.
- The table is updated by hand when OpenAI announces a new wave; `tableVerified` in the summary row shows the date.

Need it fixed before the deadline? Migration Pack from $99, fixed price with before/after proof: https://mdfifty50-boop.github.io/openai-sunset-check/

# Actor input Schema

## `text` (type: `string`):

An exported n8n workflow, a Make blueprint, a code file, a .env or any text. JSON is parsed so hits point to the node and field.

## `textName` (type: `string`):

Shown as the file name in results (e.g. lead-bot.json). Optional.

## `githubRepoUrl` (type: `string`):

https://github.com/owner/repo (optionally /tree/branch). Every text file is scanned; node_modules, lock files, binaries and files over 1 MB are skipped. Up to 4,000 files.

## `githubRef` (type: `string`):

Defaults to the repo's default branch.

## `includeAlreadyShutDown` (type: `boolean`):

Also report references to models whose shutdown date has passed (gpt-3.5-turbo, gpt-4, o1, dall-e-3, Assistants API...). These calls fail today.

## Actor input object example

```json
{
  "text": "{\"nodes\":[{\"name\":\"OpenAI Chat Model\",\"type\":\"@n8n/n8n-nodes-langchain.lmChatOpenAi\",\"parameters\":{\"model\":{\"__rl\":true,\"value\":\"gpt-4o-mini\",\"mode\":\"list\"}}}]}",
  "includeAlreadyShutDown": true
}
```

# Actor output Schema

## `results` (type: `string`):

No description

## `report` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "text": "{\"nodes\":[{\"name\":\"OpenAI Chat Model\",\"type\":\"@n8n/n8n-nodes-langchain.lmChatOpenAi\",\"parameters\":{\"model\":{\"__rl\":true,\"value\":\"gpt-4o-mini\",\"mode\":\"list\"}}}]}"
};

// Run the Actor and wait for it to finish
const run = await client.actor("fifty50labs/openai-deprecation-scanner").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "text": "{\"nodes\":[{\"name\":\"OpenAI Chat Model\",\"type\":\"@n8n/n8n-nodes-langchain.lmChatOpenAi\",\"parameters\":{\"model\":{\"__rl\":true,\"value\":\"gpt-4o-mini\",\"mode\":\"list\"}}}]}" }

# Run the Actor and wait for it to finish
run = client.actor("fifty50labs/openai-deprecation-scanner").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "text": "{\\"nodes\\":[{\\"name\\":\\"OpenAI Chat Model\\",\\"type\\":\\"@n8n/n8n-nodes-langchain.lmChatOpenAi\\",\\"parameters\\":{\\"model\\":{\\"__rl\\":true,\\"value\\":\\"gpt-4o-mini\\",\\"mode\\":\\"list\\"}}}]}"
}' |
apify call fifty50labs/openai-deprecation-scanner --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,fifty50labs/openai-deprecation-scanner"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/lSUhefDMBZBsKteFE/builds/mMjYFGba5zA2IYCiu/openapi.json