DEV Community: AI Deprecations

What to Do Before OpenAI GPT-5 and o3 Shut Down on December 11, 2026

AI Deprecations — Fri, 06 Nov 2026 07:23:06 +0000

OpenAI removes gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3, o3-pro and their dated snapshots from the API on Dec 11, 2026 (announced Jun 11, 2026).

Free Mon/Wed/Fri email + breaking shutdown alerts (every date linked to the official source): Subscribe at aideprecations.com/subscribe. Double opt-in. Confirming also unlocks the AI Model Migration Checklist and a personal .ics shutdown calendar.

Every affected model ID and its replacement

Model ID	Platform	Shutdown	Replacement (provider wording)
`gpt-5`	OpenAI	Dec 11, 2026	`gpt-5.6-sol`
`gpt-5-2025-08-07`	OpenAI	Dec 11, 2026	`gpt-5.6-sol`
`gpt-5-mini`	OpenAI	Dec 11, 2026	`gpt-5.6-terra`
`gpt-5-mini-2025-08-07`	OpenAI	Dec 11, 2026	`gpt-5.6-terra`
`gpt-5-nano`	OpenAI	Dec 11, 2026	`gpt-5.6-luna`
`gpt-5-nano-2025-08-07`	OpenAI	Dec 11, 2026	`gpt-5.6-luna`
`gpt-5-pro`	OpenAI	Dec 11, 2026	`gpt-5.6-sol` (`reasoning.mode: pro`)
`gpt-5-pro-2025-10-06`	OpenAI	Dec 11, 2026	`gpt-5.6-sol` (`reasoning.mode: pro`)
`o3`	OpenAI	Dec 11, 2026	`gpt-5.6-sol`
`o3-2025-04-16`	OpenAI	Dec 11, 2026	`gpt-5.6-sol`
`o3-pro`	OpenAI	Dec 11, 2026	`gpt-5.6-sol` (`reasoning.mode: pro`)
`o3-pro-2025-06-10`	OpenAI	Dec 11, 2026	`gpt-5.6-sol` (`reasoning.mode: pro`)

Source: OpenAI API deprecations ("2026-06-11: GPT-5 and o3 model deprecations").

Fine-tuned models: OpenAI says fine-tuned versions follow the same shutdown schedule as their underlying base models.
Pro models: the replacement for gpt-5-pro and o3-pro is written as gpt-5.6-sol with reasoning.mode: pro — the model ID changes and you set a reasoning mode. Swapping the ID alone is not the documented replacement.
Aliases vs snapshots: both the alias (gpt-5) and the dated snapshot (gpt-5-2025-08-07) are on the list. Pinning a snapshot does not save you.
Azure OpenAI deployments follow Azure's own retirement schedule; check the Azure OpenAI page, not this date.

Step 1: Find every call site

rg -n --hidden -g '!node_modules' -e '"gpt-5(-mini|-nano|-pro)?(-20[0-9-]+)?"' -e '"o3(-pro)?(-20[0-9-]+)?"' .
rg -n --hidden -g '*.{yml,yaml,json,toml,tf,tfvars}' -g '.env*' -e 'gpt-5' -e '\bo3\b' .

Note the quotes in the first pattern: they avoid matching newer IDs like gpt-5.1 or gpt-5.6-sol. Review the hits by hand. Also check CI workflows, eval configs, LLM gateways/routers, feature flags, and fine-tune job configs.

Step 2: Map each model to its replacement

gpt-5, o3 → gpt-5.6-sol
gpt-5-mini → gpt-5.6-terra
gpt-5-nano → gpt-5.6-luna
gpt-5-pro, o3-pro → gpt-5.6-sol with reasoning.mode: pro

Confirm in OpenAI's model docs before switching.

Step 3: Re-test what actually breaks

Reasoning parameters: o3 and gpt-5 accept reasoning-effort settings; confirm which settings the replacement accepts and pin them explicitly.
Tool calls: validate every function call against your JSON schema and re-run multi-step agent loops end to end.
Structured outputs: parse every response with your production parser; compare refusal and truncation rates.
Cost and latency: measure on your own traffic; pro reasoning modes can be much slower.

Step 4: Roll out in stages before Dec 11

Model ID and reasoning settings in config, not code. Shadow traffic, then 1% → 10% → 50% → 100%. Finish at least a week before Dec 11, 2026.

Step 5: Guard against the day-after failure

Alert on model-not-found errors from the OpenAI SDK. Fail CI if any of the 12 retired IDs above appears in the repo.

Free checklist + alerts

Full guide (canonical): https://aideprecations.com/guides/gpt-5-o3-shutdown/
Subscribe (email, calendar, webhooks, MCP): https://aideprecations.com/subscribe/
Machine-readable data: https://aideprecations.com/data.json

Dates come from official provider pages. If a date looks wrong, open an issue against the source page first — that page is the source of truth.

What to Do Before Claude Sonnet 4.5 Shuts Down on November 30, 2026

AI Deprecations — Fri, 06 Nov 2026 07:23:05 +0000

Anthropic retires claude-sonnet-4-5-20250929 on the Claude API on Nov 30, 2026. After that date, requests to it fail. Anthropic's recommended replacement is claude-sonnet-5-5.

Free Mon/Wed/Fri email + breaking shutdown alerts (every date linked to the official source): Subscribe at aideprecations.com/subscribe. Double opt-in. Confirming also unlocks the AI Model Migration Checklist and a personal .ics shutdown calendar.

The facts (from official pages)

Model ID	Platform	Shutdown	Replacement
`claude-sonnet-4-5-20250929`	Anthropic Claude API	Nov 30, 2026	`claude-sonnet-5-5` (source)
`anthropic.claude-sonnet-4-5-20250929-v1:0`	AWS Bedrock	Apr 8, 2027	not listed (source)

Anthropic deprecated claude-sonnet-4-5-20250929 on Sep 30, 2026 and retires it on the Claude API on Nov 30, 2026 (Anthropic model deprecations).

AWS Bedrock is different: anthropic.claude-sonnet-4-5-20250929-v1:0 was marked deprecated on Oct 8, 2026 with a shutdown date of Apr 8, 2027. AWS does not list a replacement on that page (AWS Bedrock model lifecycle).

Google Vertex AI publishes its own retirement dates for partner models — check Google's page directly. Do not assume it matches the Claude API date.

Step 1: Find every place you call it

rg -n --hidden -g '!node_modules' 'claude-sonnet-4-5' .
rg -n --hidden -g '*.{yml,yaml,json,toml,tf,tfvars}' -g '.env*' 'sonnet-4-5' .

Check CI workflows, Dockerfiles, notebooks, eval configs, LLM gateway/router configs, feature flags and prompt registries. On Bedrock, the ID looks like anthropic.claude-sonnet-4-5-20250929-v1:0 (often with a region or inference-profile prefix); search for sonnet-4-5 to catch every form.

Step 2: Map each call to its platform and date

The same model retires on different days depending on where you call it. Write down, per call site: platform (Claude API / Bedrock / Vertex / gateway), model ID, shutdown date, owner.

Step 3: Test the replacement

Run claude-sonnet-5-5 against a frozen set of real prompts and compare quality, refusals, latency and cost.

Tool use: confirm every tool call still validates against your schemas and that multi-step tool loops end the same way.
Structured output: parse 100% of responses with your real JSON parser, not by eye.
Parameters: re-check max output tokens, thinking/extended-reasoning settings and any beta headers against Anthropic's docs for the new model.

Step 4: Roll out in stages, well before Nov 30

Put the model ID in config, not code, so rollback is one change. Shadow traffic first, then 1% → 10% → 50% → 100%. Aim to finish at least a week before Nov 30, 2026.

Step 5: Guard against the day-after failure

Alert on model-not-found / 404 errors from the Anthropic SDK. Add a CI check that fails if claude-sonnet-4-5-20250929 appears in the repo after the cutover.

Free checklist + alerts

Full guide (canonical): https://aideprecations.com/guides/claude-sonnet-4-5-shutdown/
Subscribe (email, calendar, webhooks, MCP): https://aideprecations.com/subscribe/
Machine-readable data: https://aideprecations.com/data.json

Dates come from official provider pages. If a date looks wrong, open an issue against the source page first — that page is the source of truth.