Anthropic API · 17 days left

Claude Sonnet 4.5 API shutdown: November 30, 2026

Anthropic is removing Claude Sonnet 4.5 from its API on November 30, 2026. Any request that still uses claude-sonnet-4-5-20250929 will fail from that day. The replacement Anthropic lists is claude-sonnet-5-5.

What to do before November 30

1. Find every place the ID is used. Search your code, environment variables, prompt management tools and scheduled jobs for claude-sonnet-4-5-20250929. Fine tuned versions follow the base model's schedule.
2. Run your real prompts on both models. Take ten to fifty real inputs and compare the answers from claude-sonnet-4-5-20250929 and claude-sonnet-5-5 side by side. Look first at anything your code parses: JSON, labels, numbers, tool arguments.
3. Save the old answers. After the shutdown you cannot ask Claude Sonnet 4.5 anything again. A saved baseline lets you check any later model against it.
4. Switch, then watch. Change the model ID, deploy, and watch latency, token usage and error rates for the first days.

Compare claude-sonnet-4-5-20250929 with claude-sonnet-5-5 now

Free for three prompts. Runs in your browser with your own Anthropic key. Nothing is sent to us.

What usually changes in a model swap

The replacement is normally the stronger model, so quality is rarely the problem. The breaks come from code that expected the old model's habits:

• JSON answers that arrive inside a code fence, or with a key renamed, added or missing.
• Plain text answers that come back with markdown headings, bold text or bullet lists.
• Answers that are much longer or shorter, which shifts cost and can overflow a user interface.
• One word classifications that flip on borderline inputs.
• Refusals or added caveats on inputs the old model answered directly.
• Different latency and output token counts for the same request.

Questions

When is Claude Sonnet 4.5 shut down?

Anthropic lists November 30, 2026 as the date claude-sonnet-4-5-20250929 is removed from the API. After that date requests to that model ID fail.

What replaces Claude Sonnet 4.5?

Anthropic's deprecation page lists claude-sonnet-5-5 as the replacement.

Will my prompts behave the same on claude-sonnet-5-5?

Usually close, and often better, but not identical. The common breaks are structural: JSON that gains a code fence or loses a key, markdown where plain text used to be, longer or shorter answers, a label that flips. The only way to know is to run your own prompts on both models while the old one still answers.

Can I still test against Claude Sonnet 4.5 after November 30, 2026?

Not against the live model. If you save its answers to your prompts before November 30, 2026, you can compare any later model against that saved baseline.