Free tool · data

Model deprecation and shutdown tracker

On this page

The short answer

  • Next shutdown, 30 Nov 2026: OpenAI Evals dashboard, API and graders for eval workflows, OpenAI /v1/prompts and reusable prompt objects, OpenAI Agent Builder, Anthropic claude-sonnet-4-5-20250929.
  • 21 dated shutdowns are still ahead as of 13 Nov 2026; 17 of them fall within the next 90 days.
  • 1 Dec 2026: Google routes gemini-2.5-pro and gemini-2.5-flash to newer models. 11 Dec 2026: OpenAI shuts down gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3 and o3-pro.
  • Every row comes from the provider's official deprecations page, read 13 Nov 2026, with a link. Get an email when a new date is published.

Key numbers

  • OpenAI shuts down gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3 and o3-pro on 11 Dec 2026 (replacements: gpt-6.1-sol, gpt-6.1-terra, gpt-6-luna). (OpenAI deprecations page, 13 Nov 2026)
  • Anthropic retires claude-sonnet-4-5-20250929 on 30 Nov 2026; the recommended replacement is claude-sonnet-5-5. (Anthropic model deprecations, 13 Nov 2026)
  • From 1 Dec 2026, Gemini API requests to gemini-2.5-pro route to gemini-3.8-flash and are billed at its rates. (Gemini API deprecations, 13 Nov 2026)

Tracker

Data (JSON, CC BY 4.0)

39 entries.

Model and feature shutdowns, soonest first (provider pages read 13 Nov 2026). “Days” is computed in your browser from today's date.
Model or featureStatusShutdownDaysOfficial replacementNoticeSource
gemini-3-pro-previewGoogleShut down—gemini-3.1-pro-preview—Google
claude-3-haiku-20240307AnthropicRetired—claude-haiku-4-5-2025100119 Feb 2026Anthropic
gemini-2.0-flash, gemini-2.0-flash-liteGoogleShut down—gemini-3.6-flash / gemini-3.1-flash-lite—Google
claude-sonnet-4-20250514AnthropicRetired—claude-sonnet-5-514 Apr 2026Anthropic
claude-opus-4-20250514AnthropicRetired—claude-opus-4-814 Apr 2026Anthropic
claude-opus-4-1-20250805AnthropicRetired—claude-opus-4-85 Jun 2026Anthropic
temperature, top_p, top_k request parametersAnthropic · featureRemoved in API version 2026-10-21—Omit them and guide behavior with the prompt—Anthropic
gpt-3.5-turbo (incl. 0125)OpenAIShut down—gpt-5.6-terra22 Apr 2026OpenAI
gpt-4, gpt-4-turbo, gpt-4-0613OpenAIShut down—gpt-5.6-sol22 Apr 2026OpenAI
gpt-4.1-nanoOpenAIShut down—gpt-5.6-luna22 Apr 2026OpenAI
o1, o1-pro, o3-mini, o4-miniOpenAIShut down—gpt-5.6-sol (o4-mini: gpt-5.6-terra)22 Apr 2026OpenAI
claude-sonnet-4-5-20250929AnthropicDeprecated—claude-sonnet-5-530 Sep 2026Anthropic
Evals dashboard, API and graders for eval workflowsOpenAI · featureRead-only—Promptfoo (OpenAI's recommendation)3 Jun 2026OpenAI
/v1/prompts and reusable prompt objectsOpenAI · featureDeprecated—Move prompt content into your application code3 Jun 2026OpenAI
Agent BuilderOpenAI · featureDeprecated—Agents SDK or ChatGPT Workspace Agents3 Jun 2026OpenAI
gemini-2.5-proGoogleDeprecated—gemini-3.8-flash (requests auto-route from 1 Dec 2026, billed at Gemini 3.8 Flash rates)—Google
gemini-2.5-flashGoogleDeprecated—gemini-3.5-flash-lite (requests auto-route from 1 Dec 2026, billed at Gemini 3.5 Flash-Lite rates)—Google
gpt-5OpenAIDeprecated—gpt-6.1-sol11 Jun 2026OpenAI
gpt-5-miniOpenAIDeprecated—gpt-6.1-terra11 Jun 2026OpenAI
gpt-5-nanoOpenAIDeprecated—gpt-6-luna11 Jun 2026OpenAI
gpt-5-proOpenAIDeprecated—gpt-6.1-sol (reasoning.mode: pro) in the Responses API11 Jun 2026OpenAI
o3OpenAIDeprecated—gpt-6.1-sol11 Jun 2026OpenAI
o3-proOpenAIDeprecated—gpt-6.1-sol (reasoning.mode: pro) in the Responses API11 Jun 2026OpenAI
gpt-4o (2024-08-06, 2024-11-20)OpenAIDeprecated—gpt-6-luna14 Oct 2026OpenAI
gpt-4o-mini (2024-07-18)OpenAIDeprecated—gpt-6-luna14 Oct 2026OpenAI
gpt-4.1 (2025-04-14)OpenAIDeprecated—gpt-6-luna14 Oct 2026OpenAI
gpt-4.1-mini (2025-04-14)OpenAIDeprecated—gpt-6-luna14 Oct 2026OpenAI
gpt-5.5-cyber-previewOpenAIDeprecated—The most capable cyber model available to you5 Nov 2026OpenAI
gpt-5.3-codexOpenAIDeprecated—gpt-6-sol1 Oct 2026OpenAI
gpt-5.4-nanoOpenAIDeprecated—gpt-6-luna1 Oct 2026OpenAI
gpt-5.1OpenAIDeprecated—gpt-6-sol1 Oct 2026OpenAI
gemini-3.1-flash-liteGoogleScheduled—gemini-3.5-flash-lite—Google
claude-mythos-previewAnthropicDeprecatedTo be announced—Not listed9 Jun 2026Anthropic
claude-opus-4-5-20251101AnthropicActiveNot sooner than 24 Nov 2026—Not deprecated yet—Anthropic
claude-haiku-4-5-20251001AnthropicActiveNot sooner than 15 Oct 2026 (date passed, no deprecation listed)—Not deprecated yet—Anthropic
claude-opus-4-6AnthropicActiveNot sooner than 5 Feb 2027—Not deprecated yet—Anthropic
claude-sonnet-4-6AnthropicActiveNot sooner than 17 Feb 2027—Not deprecated yet—Anthropic
gemini-3.7-flashGoogleRedirectedEndpoint stays; requests route to gemini-3.8-flash—gemini-3.8-flash—Google
gemini-3.5-flashGoogleRedirectedEndpoint stays; requests route to gemini-3.6-flash—gemini-3.6-flash—Google

Scope: Text and chat models (plus a few platform features) from each provider's official deprecations page. Image, audio, realtime and embedding models are left out. Dates are as published by the provider on the day we read the page; the provider page is authoritative.

Get model deprecation alerts

We email you when OpenAI, Anthropic or Google publish a new shutdown date for a model on our tracker. Sent by hand from hello@litmiq.com, a few times a month at most. Unsubscribe by replying.

We store only your email, through our form provider. See the privacy policy.

Notice periods

Minimum notice before a model is retired, per each provider's page (read 13 Nov 2026)
ProviderPolicy
OpenAIGenerally available models: at least 6 months' notice. Specialized variants: at least 3 months. Preview models: may be much shorter, such as 2 weeks.
AnthropicAt least 60 days' notice before retirement for publicly released models. Dates apply to Anthropic-operated platforms; Bedrock and Google-managed Vertex set their own schedules.
GoogleListed shutdown dates are the earliest possible dates; Google says it will communicate the exact date with advance notice.

How to migrate before a shutdown

  1. Find every pinned model ID in code, config and evals, including old snapshot names.
  2. Run the same test cases on the current model and the replacement, plus one cheaper tier. Compare outputs, latency and cost before you switch production traffic.
  3. Read the cases that changed, not just the average: format, refusals and policy answers break first. Our model migration testing guide has a 4-step test and a ready smoke-test suite.
  4. Price the switch with the token and cost calculator. Auto-routed Gemini models are billed at the new model's rates.

Sources (read 13 Nov 2026)

Embed this tool

Paste this HTML on your page. The iframe loads a noindex, in-browser copy of the tool. Please keep the credit link. Other sites may frame only these embed URLs.

Standalone embed URL: /embed/model-deprecation-tracker.

Useful for your docs, README or team wiki? Copy a link or badge. It's free to use and needs no account.

Preview of the badge.

FAQ

Which LLM shuts down next?

As read on 13 Nov 2026: on 30 Nov 2026, OpenAI Evals dashboard, API and graders for eval workflows; OpenAI /v1/prompts and reusable prompt objects; OpenAI Agent Builder; Anthropic claude-sonnet-4-5-20250929. The tracker lists every upcoming date with its official replacement.

When is gpt-5 shut down?

OpenAI's deprecations page lists gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3 and o3-pro for shutdown on 11 December 2026 (announced 11 June 2026). Replacements: gpt-6.1-sol for gpt-5 and o3, gpt-6.1-terra for gpt-5-mini, gpt-6-luna for gpt-5-nano.

When is Claude Sonnet 4.5 retired?

Anthropic's model deprecations page lists claude-sonnet-4-5-20250929 as deprecated on 30 September 2026 with retirement on 30 November 2026. The recommended replacement is claude-sonnet-5-5.

What happens to gemini-2.5-pro and gemini-2.5-flash?

Google's Gemini deprecations page says that from 1 December 2026, API requests to gemini-2.5-pro route to gemini-3.8-flash and requests to gemini-2.5-flash route to gemini-3.5-flash-lite, billed at the new model's rates.

How do the alerts work?

Leave your email and we send a short email when a provider publishes a new shutdown date for a model on the tracker. We send them by hand from hello@litmiq.com, a few times a month at most, and you can unsubscribe by replying.

How current is this?

We read each provider's page on 13 Nov 2026. Provider pages change; they are authoritative and linked on every row.

Test the replacement before the date

Open the model migration smoke test and run it on the old and new model side by side. Free, with your own key.

  • Free, no signup
  • Runs in your browser
  • Your OpenAI key, sent only to OpenAI

Follow Litmiq on LinkedIn