OpenAI is removing GPT-5 pro from its API on December 11, 2026. Any request that still uses gpt-5-pro or gpt-5-pro-2025-10-06 will fail from that day. The replacement OpenAI lists is gpt-6.1-sol. OpenAI lists the replacement as gpt-6.1-sol with reasoning mode pro in the Responses API.
| Model | GPT-5 pro |
|---|---|
| API model IDs affected | gpt-5-pro, gpt-5-pro-2025-10-06 |
| Shutdown date | December 11, 2026 |
| Replacement listed by OpenAI | gpt-6.1-sol |
| Source | OpenAI deprecation page, read November 13, 2026 |
gpt-5-pro. Fine tuned versions follow the base model's schedule.gpt-5-pro and gpt-6.1-sol side by side. Look first at anything your code parses: JSON, labels, numbers, tool arguments.Compare gpt-5-pro with gpt-6.1-sol now
Free for three prompts. Runs in your browser with your own OpenAI key. Nothing is sent to us.
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:
GPT-5, GPT-5 mini, GPT-5 nano, o3, o3-pro.
OpenAI lists December 11, 2026 as the date gpt-5-pro, gpt-5-pro-2025-10-06 are removed from the API. After that date requests to those model IDs fail.
OpenAI's deprecation page lists gpt-6.1-sol as the replacement. OpenAI lists the replacement as gpt-6.1-sol with reasoning mode pro in the Responses API.
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.
Not against the live model. If you save its answers to your prompts before December 11, 2026, you can compare any later model against that saved baseline.