Migrating Off Retired GPT Models in 2026: A Working Checklist

Last updated: June 11, 2026

OpenAI is running its largest model cleanup since the GPT-3 era. On April 22, 2026 it deprecated more than a dozen models in one sweep - GPT-4, GPT-4o snapshots, the o-series, and five Codex variants - then added the GPT-5.2 and 5.3 chat aliases on May 8. The first shutdowns land July 23, 2026.

This checklist is built from the live deprecations page as of June 11, 2026: what maps to what, the API diffs that bite, an eval-before-switch plan, the cost table, and when a retirement is the right moment to leave the platform entirely.

First, Read the Clock Correctly

OpenAI's deprecations page defines its terms precisely. "Deprecated" takes effect the moment it is announced - the model still works, but the countdown has started. "Shut down" means requests stop resolving. Stated notice: at least 6 months for GA models, 3 months for specialized variants, as little as 2 weeks for previews.

Two things people get wrong:

The base GPT-5.x models are not deprecated. As of June 11, 2026, there are no deprecation rows for gpt-5, gpt-5.1, gpt-5.2, gpt-5.3, or their mini, nano, and pro variants. What is retiring are the -chat-latest aliases and the Codex-branded variants. If you pinned a base model, you have no deadline yet.

The dates cluster into three waves. July 23, 2026 takes the GPT-5 and 5.1 chat aliases, all five Codex variants - gpt-5.2-codex included - and both deep-research models. August 10 takes the 5.2 and 5.3 chat aliases. October 23 is the big one: GPT-4, GPT-4o, GPT-3.5 Turbo, o1, o1-pro, o3-mini, and o4-mini.

What Maps to What

Every row comes from the official deprecations page, accessed June 11, 2026:

The pattern: almost everything funnels into gpt-5.5, pro-tier reasoning goes to gpt-5.5-pro, and small cheap models go to gpt-5.4-mini. The mapping is a starting point, not a verdict - o4-mini to gpt-5.4-mini is like-for-like, but gpt-4-0613 to gpt-5.5 jumps roughly three model generations and your prompts will behave differently.

Some retirements already happened: codex-mini-latest on February 12, 2026, chatgpt-4o-latest on February 17, the GPT-4o audio and realtime previews on May 7, DALL-E 2 and 3 on May 12. Check older code paths for these first.

The API Diffs That Bite

The Assistants API has about 11 weeks left

The biggest non-model deadline: the Assistants API, deprecated August 26, 2025, shuts down August 26, 2026, replaced by the Responses and Conversations APIs. Model swaps are one-line changes; this is an architecture change - threads, runs, and tool orchestration all move. Our Responses API migration walkthrough covers the mapping. Do it before the model swap so the eval suite only runs once.

Aliases retire, snapshots persist

The lesson of this wave: -chat-latest aliases retire on their own schedule regardless of the underlying model's status. Pin dated snapshots in production and keep aliases in dev only. Your inventory grep should look for both forms.

Reasoning models fold into one family

o1, o1-pro, o3-mini, o4-mini, and both deep-research models all disappear by October 23. The o-series had distinct latency and deliberation behavior that teams tuned prompts around. When those prompts move to GPT-5.5, treat them as unverified - recommended replacement does not mean behavioral equivalent.

The platform tooling is churning too

On June 3, 2026, OpenAI deprecated its hosted Evals platform, Agent Builder, and the Reusable Prompts API, all shutting down November 30, 2026. If your plan was to run comparisons in OpenAI's hosted evals UI, that tool is itself on a deprecation clock. Keep the eval harness in your own repo, pointed at whatever provider you like.

Eval Before You Switch: A Five-Day Plan

A model swap without evals is a production incident with extra steps. The plan fits in one week:

Day 1 - Inventory. Grep for every model string: gpt-4, gpt-4o, gpt-3.5, o1, o3, o4, codex, -chat-latest. Check the usage dashboard for models called from code you forgot - old Lambdas and cron jobs are where retired models hide. Tag each call site with its shutdown date.

Day 2 - Build the golden set. Pull 50 to 200 real production requests per call site, with outputs you considered good. Skew toward edge cases and past failures. Capture latency and token counts as your baseline.

Day 3 - Run side by side. Replay the golden set against the recommended replacement and at least one alternative (leaving o4-mini, test both gpt-5.4-mini and gpt-5.4). Score with whatever fits: exact match for structured output, a judge model for prose, your test suite for code.

Day 4 - Re-run the cost math. Token counts change across model generations, and cached-input pricing changes the equation for repeated system prompts. Compute real cost per request from the Day 3 runs, not sticker prices.

Day 5 - Staged cutover. Put the model name in config, not code. Ship behind a flag at 10 percent of traffic, compare error rates and output quality, then ramp. Keep the old model in the fallback path until its shutdown date - that is what the deprecation window is for.

The Cost Table

Replacement-target pricing from the official pricing page, accessed June 11, 2026, per million tokens:

Batch processing is a flat 50 percent discount across the family. The retired models no longer appear on the pricing page at all - one more reason to capture per-request cost on Day 2 while the old model still runs.

Two routing notes. First, gpt-5.4 at $2.50/$15 is half the price of gpt-5.5 - if your gpt-4o workload never pushed capability limits, evaluate the cheaper target first. Second, cached input at one tenth of the base rate rewards putting static system prompts and tool definitions first in every request. The cross-provider picture is in our frontier model API pricing roundup; the GPT-5.5 developer guide covers what changes at the API surface.

Azure Runs on a Different Clock

If you consume these models through Microsoft Foundry (formerly Azure OpenAI), the dates above do not apply to you. Azure publishes its own model lifecycle and retirement policy: GA models get an 18-month lifecycle, new-customer access ends at 12 months, and retired models return 410 Gone.

The sharpest difference is auto-upgrades. Azure force-upgrades Standard deployments at retirement - when gpt-4o versions 2024-05-13 and 2024-08-06 retired on March 31, 2026, those deployments were auto-upgraded to gpt-5.1. A silent three-generation jump is not something you want to learn about from a customer ticket. Set versionUpgradeOption deliberately: NoAutoUpgrade means the deployment stops at retirement, which is at least a loud failure. Provisioned deployments are never auto-upgraded. Fine-tuned models get their own schedule - gpt-4o fine-tune deployments survive on Azure until October 1, 2027.

When to Jump Providers Entirely

A forced migration is the cheapest moment to re-evaluate the platform decision - you are paying the eval and cutover cost anyway. Testing a third provider on Day 3 costs one more column in the results spreadsheet.

Alternatives at the tiers people are leaving, per official pricing pages accessed June 11, 2026 (input/output per MTok):

Anthropic's pricing is structurally similar to OpenAI's - 0.1x cache reads, 50 percent batch discount - and Opus 4.8 undercuts gpt-5.5 on output at the same input price; start with our Fable 5 migration notes if that is the path. DeepSeek's V4 pricing is the aggressive option; its API speaks both OpenAI and Anthropic wire formats, making it cheap to include in a bake-off - see the deepseek-chat to V4 migration guide.

The honest caveat: switching providers does not get you off the deprecation treadmill. DeepSeek deprecates its legacy deepseek-chat and deepseek-reasoner model names on July 24, 2026. Anthropic lists Opus 4.1, Opus 4, and Sonnet 4 as deprecated right now. Every provider runs this cycle; the variables are notice and mapping quality.

When to Stay Put

Jumping providers is the wrong call more often than the pricing tables suggest. Stay if any of these hold:

• You are on a base gpt-5.x model. No deadline exists today. Doing nothing is a valid plan.
• Your eval gap is small and your integration surface is large. Structured outputs, tool calling, caching semantics, and SDK behavior all differ across providers. A 2 percent quality difference does not pay for re-testing all of that.
• Your shutdown date is October 23. A measured one-week eval in September beats a rushed cutover in June.
• You depend on provider-specific features - deep Codex integration, the Realtime API, completed compliance reviews. Re-procurement costs are real even when token prices are lower elsewhere.

The October wave is large but the process is the same at any scale: inventory, golden set, side-by-side, cost math, staged cutover. Budget one week per major call site and these deadlines are comfortable, not scary.

FAQ

Is GPT-5.4 being retired in 2026?

No. As of June 11, 2026, the deprecations page lists no shutdown for gpt-5.4 or any base GPT-5.x model. The retirements cover -chat-latest aliases, Codex variants, the o-series, and GPT-4-generation models.

What replaces GPT-4o in the OpenAI API?

OpenAI's recommendation for gpt-4o-2024-05-13 is gpt-5.5, with a shutdown date of October 23, 2026. If the workload was cost-sensitive rather than capability-bound, evaluate gpt-5.4 too - run both against a golden set first.

When does the Assistants API shut down?

August 26, 2026, one year after its deprecation announcement. The replacements are the Responses and Conversations APIs. It is an architectural migration, not a model swap, so schedule it before model changes on the same code paths.

Do Azure OpenAI retirement dates match OpenAI's dates?

No. Microsoft Foundry runs an independent 18-month lifecycle - Azure retired gpt-4o versions 2024-05-13 and 2024-08-06 on March 31, 2026, months ahead of OpenAI's October 23 API date, and auto-upgrades Standard deployments at retirement unless versionUpgradeOption says otherwise.

Sources

• OpenAI Model Deprecations - retirement table, replacement mappings, notice policy. Accessed June 11, 2026.
• OpenAI API Pricing - GPT-5.5 and GPT-5.4 family pricing. Accessed June 11, 2026.
• Microsoft Foundry Models lifecycle and support policy - Azure lifecycle, auto-upgrades, fine-tune schedules. Accessed June 11, 2026.
• Anthropic Claude API Pricing - Claude pricing, caching, batch, deprecated models. Accessed June 11, 2026.
• DeepSeek API Pricing - V4 pricing, legacy name retirement, compatible endpoints. Accessed June 11, 2026.