Are these dates official?

They reflect publicly announced or scheduled retirement dates as of the page's update date. Providers can change schedules, so always confirm against the provider's own deprecation page before relying on a date for a production migration.

How current is this list?

The list carries an update date in the page metadata. Model lifecycles move quickly, so treat it as a planning aid and verify the most time-sensitive dates directly with the provider.

Why do models get deprecated?

Providers retire older snapshots to consolidate on newer, cheaper, or more capable models, to reduce serving costs, and to address safety or licensing changes. Pinned snapshot IDs are the most likely to be retired.

What happens if I do not migrate in time?

Requests to a retired model typically start returning errors or get silently routed to a successor, which can change behaviour and break output parsing. Migrate and re-test before the date, not after.

How do I avoid surprise breakages?

Avoid hardcoding pinned snapshot IDs where you can, subscribe to your providers' deprecation notices, and keep a model inventory so you know exactly which calls to update when a date lands.

AI Model Deprecation Tracker

AI model deprecation tracker

Pinned model snapshots do not live forever. Providers retire older versions on a schedule, and a hardcoded model ID that worked for a year can start returning errors overnight. This tracker gathers announced and scheduled retirement dates across the major providers — OpenAI, Anthropic, Google, and Cohere — with a live days-remaining countdown, the recommended successor, and a short migration note for each. Filter it to the models you actually run so you only see what matters to your stack.

How it works

Each entry pairs a model with its publicly stated lifecycle status — active, deprecated, or retired — and, where one has been announced, a retirement date. The tool computes days remaining against today’s date and sorts the soonest deadlines to the top, colour-coded by urgency. You can filter by provider or paste your own model IDs to narrow the list. For every model the tracker shows a recommended replacement and a one-line migration note covering the gotchas that usually bite — changed defaults, different token limits, or output-format drift. Dates are a planning aid; always confirm against the provider’s own deprecation page before a production cutover.

How to stay ahead of retirements

Don’t hardcode pinned snapshots. Where latency-aliases like *-latest exist, they ride forward automatically; pinned IDs do not.
Keep a model inventory. You can only migrate calls you know about. Track every model ID your code references.
Subscribe to deprecation notices. Every major provider publishes them; the surprise only happens to teams who do not read them.
Migrate then re-test. Successor models change defaults and formatting. Swap the ID, then re-run your output parsing and evals before shipping.