benchr
AI model deprecation tracker
Announced retirements, confirmed sunset dates, and one-line migration paths — verified against each provider's official deprecation documentation. Migrate before the sunset date to avoid broken workloads.
Announced & confirmed sunsets
| Model | Provider | Status | Sunset date | Migrate to | Source |
|---|---|---|---|---|---|
| Gemini 3 Pro | Sunset | Mar 26, 2026 | Gemini 3.1 Pro — same pricing tier, improved reasoning. Drop-in API swap. | ai.google.dev/deprecation | |
| GPT-4o (legacy) | OpenAI | Deprecated | Feb 2026 | GPT-5 — lower price, better benchmarks. Change model id to gpt-5. |
platform.openai.com/deprecations |
| GPT-4 Turbo | OpenAI | Sunset | Jan 2026 | GPT-5 — significantly cheaper per token, longer context. Swap model id. | platform.openai.com/deprecations |
| Claude 3 Opus | Anthropic | Deprecated | TBD (no firm date) | Claude Opus 4.7 or Claude Opus 4.8 — same price, better benchmarks. | docs.anthropic.com/en/api/model-deprecations |
| Claude 3.5 Haiku | Anthropic | Deprecated | TBD (no firm date) | Claude Haiku 4.5 — same pricing tier, better capability. | docs.anthropic.com/en/api/model-deprecations |
| Gemini 1.0 Pro | Sunset | Apr 9, 2026 | Gemini 3.1 Pro or Gemini 3.5 Flash depending on quality/cost needs. | ai.google.dev/deprecation |
Active models (no announced sunset)
These models are fully supported as of June 2026 with no announced end-of-life. Still, model generations move fast — sign up for the benchr dispatch below to hear about changes same-day.
| Model | Provider | Status | Notes |
|---|---|---|---|
| Claude Opus 4.8 | Anthropic | Active | Released May 28, 2026. Current flagship. |
| Claude Opus 4.7 | Anthropic | Active | Superseded by 4.8 but still supported. |
| Claude Sonnet 4.6 | Anthropic | Active | Current mid-tier workhorse. |
| Claude Haiku 4.5 | Anthropic | Active | Current small/fast tier. |
| GPT-5.5 | OpenAI | Active | Latest OpenAI flagship (Apr 2026). |
| GPT-5 | OpenAI | Active | Launched Aug 2025. Main production model. |
| GPT-5 Mini | OpenAI | Active | Small/cheap tier. |
| Gemini 3.5 Flash | Active | GA since May 19, 2026. | |
| Gemini 3.1 Pro | Active | Preview. Replacement for Gemini 3 Pro. | |
| Grok 4.3 | xAI | Active | Current xAI flagship. |
| DeepSeek V4-Pro / Flash | DeepSeek | Active | MIT license. Self-hosted or API. |
| Kimi K2.6 | Moonshot AI | Active | Modified MIT. |
| Mistral Large 3 | Mistral | Active | Apache 2.0. Dec 2025. |
| Llama 4 Scout / Maverick | Meta | Active | Community license. Self-host. |
| Qwen 3.6 | Alibaba | Active | Apache 2.0. |
| Phi-4 | Microsoft | Active | MIT. Edge/local use. |
How to migrate safely
Model migrations are usually a one-line API change — swap the model ID in your request. The harder part is verifying that outputs haven't regressed. Here's the process benchr recommends:
- Read the provider's official migration guide — they almost always include context-window and capability notes.
- Run your top 10 prompt templates against both the old and new model. Compare outputs.
- Check for prompt-length changes — newer models sometimes handle system prompts differently.
- Update your model ID in staging first; test for at least 48 hours before production.
- Monitor cost — newer models often have different pricing even at the "same tier."
Need to quickly compare the old and new model? Use the side-by-side compare tool.
Frequently asked questions
What is model deprecation?
When a provider announces that a model version will stop accepting API calls after a specific date. Usually they give 30–90 days notice and suggest a successor model. After the sunset date, calls to that model ID will fail or redirect.
How much notice do providers give?
It varies. Anthropic and OpenAI typically give 30–90 days notice. Google has used 30-day windows. Some smaller providers give less. The benchr dispatch covers these announcements same-day — see the newsletter signup below.
Is Gemini 3 Pro still accessible?
No — Gemini 3 Pro was sunset March 26, 2026. Migrate to Gemini 3.1 Pro (same pricing, better reasoning) or Gemini 3.5 Flash (faster, cheaper, with a free tier).