Migrating from GPT-4, GPT-4 Turbo, GPT-3.5 Turbo, o1, o1-pro, o3-mini, o4-mini, GPT-4.1 nano to GPT-5.6 (Sol, Terra or Luna)
GPT-4, GPT-4 Turbo, GPT-3.5 Turbo, o1, o1-pro, o3-mini, o4-mini, GPT-4.1 nano stopped answering on Oct 23, 2026 on the OpenAI API. Requests to a retired model fail. The provider’s replacement is GPT-5.6 (Sol, Terra or Luna).
- Shutdown
- Oct 23, 2026
- Retired
- 10 days ago
- Replacement
- GPT-5.6 (Sol, Terra or Luna)
What shuts down
gpt-4and its dated snapshotsgpt-4-32kand its dated snapshotsgpt-4-turboand its dated snapshotsgpt-4o-2024-05-13and its dated snapshotsgpt-3.5-turboand its dated snapshotso1and its dated snapshotso1-miniand its dated snapshotso1-previewand its dated snapshotso1-proand its dated snapshotso3-miniand its dated snapshotso4-miniand its dated snapshotsgpt-4.1-nanoand its dated snapshotsgpt-4-1106-previewand its dated snapshots
Single-day mass shutdown. Fine-tuned models of these families were shut down too.
Source: developers.openai.com. Check your provider’s deprecations page before you plan around a date.
Find every place you use it
The free scanner flags every reference in your repository and opens one issue with the deadline:
npx swapvera-scan .Or on every push, as a GitHub Action:
- uses: pixelric-spec/swapvera-scanner@v1
with:
fail-on: retiredWhat can change when you swap the ID
Prompts tuned for one model rarely transfer perfectly to the next. Check these before you merge:
- Structured output: JSON that stays valid and keeps the same field types.
- Tool calls: the same tools called with the same arguments, and no calls where there were none.
- Instructions in your system prompt that the new model follows differently, such as length limits or policies it must quote.
- Refusals and safety behavior on your edge cases.
- Parameters the new model rejects, such as a fixed temperature on reasoning models.
- Latency and cost per call at your real input sizes.
What broke for other teams
0of 5 teams
No team has shared results for GPT-4, GPT-4 Turbo, GPT-3.5 Turbo, o1, o1-pro, o3-mini, o4-mini, GPT-4.1 nano to GPT-5.6 (Sol, Terra or Luna) yet. Nothing about a migration is published until 5 different teams have shared it, so no single team’s results can be picked out.
Add yours when you run the verdict: swapvera run --share. Only categories are sent, never prompts or outputs. See exactly what is sent.
Check the switch on your own prompts
Swapvera runs your cases on GPT-4, GPT-4 Turbo, GPT-3.5 Turbo, o1, o1-pro, o3-mini, o4-mini, GPT-4.1 nano and GPT-5.6 (Sol, Terra or Luna) and comments a verdict on the pull request: safe to migrate, review these cases, or do not migrate.