Model retirements / o3 and o3-pro
o3 and o3-pro retire from the OpenAI API on 11 December 2026.
OpenAI removes o3 and o3-pro on 11 December 2026, the same day as the gpt-5 family. The replacement for both is gpt-5.6-sol. Source: OpenAI: deprecations, checked 9 Nov 2026.
- Retirement date
- 11 December 2026
- Days left
- 21
- Official replacement
- GPT-5.6 Sol
gpt-5.6-sol
Paste your prompt. See how GPT-5.6 Sol answers it.
We run it on o3, GPT-5.6 Sol, Gemini 4 Hydrogen and Qwen4 Max: the model you're on, its official replacement and up to two cheaper current models. Same test cases for each, every answer checked, with cost and speed side by side.
$10 of free test credit · No credit card needed · We keep a pasted prompt for 24 hours (privacy)
What you give us, and what you get back.
A test we ran and published. Yours has the same columns, with the model you're on now beside its replacement.
-
1You paste a prompt
You are a customer support agent for an online store. Reply to the customer using the order details. Our policy: returns within 30 days of delivery, unworn, and the customer pays return postage unless the item is faulty.
Support replies from order details and a returns policy, without promising what the policy doesn't cover.
-
2We test it
- 18 test cases the prompt had not seen, each run twice
- 7 models answer every case
- 7 checks mark each answer right or wrong
We also rewrote the prompt once. The figures are for the rewritten prompt.
-
3You get quality, cost and speed for each model
ModelAnswers that passCost per 1,000Time per answerBest qualityGPT-6.1 Sol low thinking100% 36 of 36$1.504.5 sBest valueDeepSeek V4.1 Flash medium thinking89% 32 of 36$0.396.0 sFastest worth usingMercury 3 medium thinking81% 29 of 36$0.252.1 sBest value: DeepSeek V4.1 Flash. 89% of answers passed at $0.39 per 1,000, against 100% at $1.50 for GPT-6.1 Sol. Their likely ranges overlap, so this test alone does not show a clear lead.
Tested 4 November 2026. Cost is per 1,000 answers; time is the typical time for one answer. See every answer and the method →
What's retiring, and what replaces it
| Retiring | Official replacement | Our data |
|---|---|---|
o3o3 |
gpt-5.6-solGPT-5.6 Sol |
o3 · GPT-5.6 Sol · the two compared |
o3-proo3-pro |
gpt-5.6-sol with reasoning.mode set to proGPT-5.6 Sol |
o3-pro · GPT-5.6 Sol · the two compared |
Dated snapshots go too: o3-2025-04-16 and o3-pro-2025-06-10.
Dates and replacements are OpenAI's, from https://developers.openai.com/api/docs/deprecations. Plan to have moved before the date; check the source for any change.
Why a swap can quietly change your outputs
A replacement may score higher on benchmarks, but that doesn't mean it does your task the same way. Usually nothing errors. The answers change, and your users may notice before you do.
- Format
- The new model may wrap JSON in a code fence, add Markdown, change headings or drop a field your code reads.
- Tone
- Warmer, blunter, more formal or more chatty. It reads as a different writer.
- Refusals
- It may refuse or hedge on inputs the old model handled, or answer ones it used to decline.
- Length
- Answers often get longer or shorter. That can break a limit on screen, in an SMS or in a feed.
- Instructions
- Edge-case rules in your prompt (never mention X, always end with Y) are where models differ most.
- Cost and speed
- Price per token, tokens per answer and thinking time all change, so the cost of each answer can move even at a similar list price.
Re-test before you switch
- Find every place your code, config and environment variables name the old model ID.
- Collect 10 to 20 real inputs, including the awkward ones that went wrong before.
- Write down what a good answer does: its format, length, what it must say and must not.
- Run the old and the new model on the same prompt and the same inputs, side by side.
- Read the answers that changed, not just the pass rate.
- Compare cost and time per answer, then adjust the prompt if you need to and test again.
- Switch before the date, and keep the cases as a regression test for the next change.
We can run both sides of these swaps for you: o3 against GPT-5.6 Sol; o3-pro against GPT-5.6 Sol.