cd /news/large-language-models/your-ai-model-is-retiring-here-s-wha… · home › topics › large-language-models › article
[ARTICLE · art-172950] src=dev.to ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Your AI model is retiring. Here's what actually breaks.

A developer sent 20 pull requests to open-source apps still running soon-to-be-retired models, with 8 merged so far, and found that swapping the model name is rarely sufficient. Anthropic retires claude-sonnet-4-5-20250929 on Nov 30, 2026, and OpenAI shuts down gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3 and o3-pro on Dec 11, 2026, with migration guides flagging breaking changes to sampling parameters, content-block handling, thinking configs and tool_choice values.

recommendation

Before a model retirement date, grep code, configs, tests and docs for both alias and dated model names, then retest sampling params, content blocks, thinking configs and tool_choice against the replacement model.

more in playbook: Running AI in production
by read2 min views1 publishedNov 20, 2026

Two big deadlines are close. Anthropic retires claude-sonnet-4-5-20250929 on Nov 30, 2026, and requests to it will fail after that. OpenAI shuts down gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3 and o3-pro on Dec 11, 2026.

This month I sent 20 small pull requests to open-source apps still using models like these, and 8 have been merged so far. The lesson from all of them: changing the model name is rarely the whole job. Here's what else breaks, and the fix for each.

Search the whole repo, not just the API call: code, environment variables, config files, model dropdowns, tests, docs and examples. Search for both forms of the name, like gpt-5-mini and gpt-5-mini-2025-08-07, or claude-sonnet-4-5 and claude-sonnet-4-5-20250929.

Anthropic's replacement is claude-sonnet-5-5. Its migration guide lists several changes that turn working requests into errors:

temperature, top_p and top_k. content[0].text breaks. Read content blocks by their type. This is the bug I fixed in budget_tokens with thinking: {"type": "adaptive"} and an output_config.effort level.{"type": "disabled"} returns a 400 error; send {"type": "between_tools"} instead.tool_choice of any or tool returns a 400 error; use auto with strict tools.max_tokens, limits and cost. OpenAI's deprecations page lists these replacements:

| Shutting down Dec 11 | Recommended replacement |

|---|---|
| `gpt-5` ,`o3` | `gpt-6.1-sol` | 
| `gpt-5-pro` ,`o3-pro` | `gpt-6.1-sol` with`reasoning.mode: pro` (Responses API) | 
| `gpt-5-mini` | `gpt-6.1-terra` | 
| `gpt-5-nano` | `gpt-6-luna` | 

What to test after you switch:

gpt-5-mini to gpt-5.6-terra, the maintainer added one more commit before merging: "disable Terra reasoning when using function tools" (minimal. llama-3.3-70b-versatile and llama-3.1-8b-instant on Aug 16; calls to them now return errors.grok-4.3, which bills at its own rate.

If you maintain an open-source app still on one of these models, tell me and I'll send a free PR. If you'd rather have it done in your private code, I do it for a fixed price, from $400 per repo, paid after you've reviewed it: [your email], or github.com/SamHofmannOfficial. I used AI tools to help research and write this guide.

── more in #large-language-models 4 stories · sorted by recency
── more on @anthropic 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/your-ai-model-is-ret…] indexed:0 read:2min 2026-11-20 · —