Current and upcoming shutdowns in 2026
Each model below has an announced end date from its provider. The migration column is the provider's official pick. Where benchr's pick differs (usually on price), the linked page explains why.
| Model | Provider | Shuts down | Official replacement | Details |
|---|---|---|---|---|
| Claude Opus 4.1 | Anthropic | Aug 5, 2026 | Claude Opus 4.8 | Migration page |
| GPT-5.2 / GPT-5.3 chat-latest | OpenAI | Aug 10, 2026 | GPT-5.6 Sol | Later chat-latest wave; separate from the July 23 records |
| Assistants API | OpenAI | Aug 26, 2026 | Responses + Conversations API | Platform retirement, not a model |
| Sora 2 / Sora 2 Pro | OpenAI | Sep 24, 2026 | None listed | Videos API sunsets the same day; see the video roundup |
| Gemini 2.5 Pro | Oct 16, 2026 | Gemini 3.1 Pro Preview | Migration page | |
| Gemini 2.5 Flash | Oct 16, 2026 | Gemini 3.6 Flash | Migration page; input price rises 5× | |
| GPT-4o | OpenAI | Oct 23, 2026 | GPT-5.5 | Migration page |
| GPT-4, GPT-4 Turbo, GPT-3.5 | OpenAI | Oct 23, 2026 | GPT-5.5 / GPT-5.4 mini | October wave page |
| o1, o1-pro, o3-mini, o4-mini | OpenAI | Oct 23, 2026 | GPT-5.5 / GPT-5.5 Pro | October wave page |
| GPT-4.1 nano, GPT Image 1 | OpenAI | Oct 23, 2026 | GPT-5.4 nano / GPT Image 2 | gpt-4.1 and 4.1-mini have no announced date |
| Prompts API · Evals · Agent Builder | OpenAI | Nov 30, 2026 | Agents SDK (Agent Builder) | Platform retirements, announced June 3, 2026 |
| GPT Image 1 mini / 1.5 | OpenAI | Dec 1, 2026 | GPT Image 2 | Announced June 2, 2026 |
| Older GPT-5 / o3 snapshots | OpenAI | Dec 11, 2026 | GPT-5.5 / 5.4 mini / 5.4 nano / 5.5 Pro | Dated snapshots only (gpt-5-2025-08-07, o3-2025-04-16, …); floating aliases stay. Announced June 11, 2026 |
The 2026 retirement timeline
- Mar 9Gemini 3 Pro Preview
Shut down on the Gemini API after under four months. Vertex AI listed it discontinued by March 26.
- Apr 20Claude Haiku 3
Retired. The last Claude 3-generation model to go.
- May 12DALL-E 2 and 3
Removed from the API in favor of GPT Image 2.
- Jun 1Gemini 2.0 Flash family
Shut down. Google's current recommended path is Gemini 3.6 Flash.
- Jun 15Claude Sonnet 4 + Opus 4
Both retired on the Claude API. The Claude 4.x line replaces them at the same or lower price.
- Jun 25Gemini image previews
Gemini 3 Pro Image Preview and 3.1 Flash Image Preview shut down; the stable gemini-3-pro-image and gemini-3.1-flash-image replace them.
- Jul 23OpenAI legacy IDs
Five Codex IDs, both deep-research snapshots, computer-use-preview, and two chat snapshots retired on their recorded deadline.
- Jul 24DeepSeek aliases + Opus 4.7 fast mode
DeepSeek's legacy aliases became inaccessible after 15:59 UTC; Opus 4.7 fast requests now return an error. Standard Opus 4.7 remains available.
- Aug 5Claude Opus 4.1
Retires exactly one year after its August 5, 2025 release.
- Oct 16Gemini 2.5 Pro + Flash
Both model IDs share the same recorded retirement date. The listed replacements cost more in this comparison, so recalculate the workload before cutover.
- Oct 23OpenAI model-ID retirements
The recorded date covers GPT-4o, GPT-4, GPT-4 Turbo, GPT-3.5 Turbo, GPT-4.1 nano, GPT Image 1, o1, o1-pro, o3-mini, and o4-mini IDs.
How each provider retires models
Anthropic labels models active, legacy, deprecated, then retired, and commits to at least 60 days' notice for publicly released models. Each active model carries a published "not sooner than" date: Opus 4.8, for instance, won't retire before May 28, 2027. Dates apply to the Claude API, AWS, and Microsoft Foundry; Bedrock and Vertex run their own schedules. Anthropic has also committed to preserving model weights and says it hopes to make past models available again someday.
OpenAI gives at least six months for generally available models, three for specialized variants, and as little as two weeks for previews. The April 22, 2026 announcement that ends the GPT-4 era was the largest single deprecation notice any provider has issued — and it didn't stop at models. A follow-up on June 3 scheduled three platform products for November 30: the Reusable Prompts API, the Evals dashboard and API, and Agent Builder (whose official path forward is the Agents SDK).
Google publishes earliest-possible shutdown dates rather than firm ones, then confirms exact dates closer in. Preview models can go fast. Gemini 3 Pro Preview lasted 16 weeks.
Past recorded retirement dates
| Model | Provider | Recorded date | Successor |
|---|---|---|---|
| o3 / o4-mini-deep-research | OpenAI | Jul 23, 2026 | GPT-5.5 Pro |
| gpt-5 / 5.1-chat-latest | OpenAI | Jul 23, 2026 | GPT-5.5 |
| Codex models (gpt-5-codex → 5.2-codex) | OpenAI | Jul 23, 2026 | GPT-5.5 / GPT-5.4 mini |
| computer-use-preview | OpenAI | Jul 23, 2026 | GPT-5.4 mini |
| deepseek-chat / deepseek-reasoner (legacy aliases) | DeepSeek | Jul 24, 2026 | DeepSeek V4-Flash / V4-Pro |
| Claude Opus 4.7 fast mode | Anthropic | Jul 24, 2026 | Claude Opus 4.8 fast mode |
| Gemini 3 Pro Image Preview | Jun 25, 2026 | Gemini 3 Pro Image (stable) | |
| Gemini 3.1 Flash Image Preview | Jun 25, 2026 | Gemini 3.1 Flash Image (stable) | |
| Claude Sonnet 4 | Anthropic | Jun 15, 2026 | Claude Sonnet 4.6 |
| Claude Opus 4 | Anthropic | Jun 15, 2026 | Claude Opus 4.8 |
| Gemini 2.0 Flash family | Jun 1, 2026 | Gemini 3.6 Flash | |
| DALL-E 2 / DALL-E 3 | OpenAI | May 12, 2026 | GPT Image 2 |
| Claude Haiku 3 | Anthropic | Apr 20, 2026 | Claude Haiku 4.5 |
| Gemini 3 Pro Preview | Mar 9, 2026 | Gemini 3.1 Pro Preview | |
| Claude Sonnet 3.7 | Anthropic | Feb 19, 2026 | Claude Sonnet 4.6 |
| Claude Haiku 3.5 | Anthropic | Feb 19, 2026 | Claude Haiku 4.5 |
| Claude 3 Opus | Anthropic | Jan 5, 2026 | Claude Opus 4.8 |
| Claude Sonnet 3.5 (both snapshots) | Anthropic | Oct 28, 2025 | Claude Sonnet 4.6 |
A 15-minute model-ID audit
Older model IDs often remain in production configuration after a newer default ships. Run these three checks:
1. Grep your codebase for every model string in the tables above, including date-suffixed snapshots like gpt-4o-2024-05-13 and claude-sonnet-4-20250514. Aliases hide in config files and environment variables, not just code.
Already seeing failures? A retired ID surfaces as model_not_found on OpenAI and not_found_error on Anthropic — the error database has the per-provider diagnosis and code fixes.
2. Pull your usage export. Anthropic's console has a per-key, per-model CSV export. OpenAI's usage dashboard breaks down by model. Five minutes tells you which deprecated IDs still get real traffic.
3. Price the replacement before you swap. Same-provider upgrades aren't always neutral. Gemini 2.5 Flash users face a 5× input price jump, while Claude Opus 4 users save two-thirds. Run your token volumes through the cost calculator before picking the target, and check the current rankings in case a different provider now fits better.