OpenAI Model Shutdown Scanner (n8n, Make, code, GitHub repos)

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:

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

Output

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

{
  "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, 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/