Article
November 21, 2025
Introducing GPT-5.1
# Work Users
A smarter, more conversational ChatGPT
NEW: Introducing GPT-5.1 for Work
GPT-5.1 is a smarter, more conversational version of GPT-5.
In August 2025, we released GPT-5, which automatically adapted to your task, delivering faster, higher-quality, and more reliable results. In November 2025, we released GPT-5.1, which is even faster for routine tasks and deeper on complex problems.
What’s different?
GPT-5.1 combines clearer reasoning and kinder, more helpful responses. In practice, this model upgrade means more thorough answers for complex requests and less waiting for simpler ones.
- GPT-5.1 is faster, and can use adaptive reasoning to decide when to think before responding to more challenging questions.
- GPT-5.1-Thinking adapts its thinking time more precisely to the question—spending more time on complex problems while responding more quickly to simpler ones.
When you choose GPT-5.1-Thinking, you also now have the ability to choose a “thinking time”, which gives even more granular control over reasoning effort.
Please note that Custom GPTs will be transitioning to using GPT-5.1 on January 12, 2025. We strongly recommend testing and moving custom GPTs to GPT-5.1 as soon as possible. See more about custom GPTs on GPT-5.1 in our Help Center.
What’s better about GPT-5.1?
- Clearer, more natural communication tuned for business contexts
- Stronger adaptive reasoning — responds quickly to simple tasks and adds deeper reasoning where problems demand it, improving both latency and relevance for mixed workloads.
- Improved instruction-following that reduces iteration and makes automation flows more predictable
- New personalities — greater flexibility in how ChatGPT responds. In the Personalization menu, you can choose a Base Tone and Style, for a consistent voice, tone, and interaction style across sessions. We’ll be adding in additional controls in these personalization settings over the coming weeks.
See how different base personalities respond to the same prompt:
Try GPT-5.1 out for yourself:
Faster at simple tasks
Use GPT-5.1 for tasks that don’t require advanced reasoning:
Write a short email (5–7 sentences) to my team explaining [topic, e.g. “that we’re moving to a new project management tool next month”].
The tone should be [tone, e.g. “friendly but direct”]. Include:
- Why this matters
- What’s changing
- What they need to do next
Deeper reasoning for more complex tasks
GPT-5.1-Thinking works best more complex or ambiguous tasks:
Act as a senior strategy and communication partner.
Attached is: A draft announcement about [initiative or change], a short description of our company and goals, and a list of key stakeholders (with roles + likely concerns).
1. Analyze the announcement and identify hidden risks, gaps, or ambiguities that could confuse or worry stakeholders
2. Group stakeholder concerns by persona (e.g., execs, managers, ICs) and predict their top 3 questions or objections per group.
3. Propose a communication plan (email + live meeting + FAQ) that addresses those objections proactively.
4. Rewrite the announcement so it:
- Uses clear, plain language
- Explains the “why” behind the change Makes timelines and next steps unambiguous
- Highlights benefits tailored to each stakeholder group
At the end, list any open questions you’d want me to answer before sending this out.
Key actions for admins
Review and test custom GPTs
We’ll be automatically updating all custom GPTs to GPT-5.1 on January 12, 2025. We strongly recommend testing and moving custom GPTs to GPT-5.1 as the recommended model as soon as possible. We especially recommend testing business-critical custom GPTs with Actions. See more about custom GPTs with Actions in our Help Center.
Share the announcement with your team
This is a great time to explore new use cases for work, refresh training on best practices, and encourage your team to experiment. Share resources on the OpenAI Academy for Work, and use the sample messaging below to explain the model change:
Hey team! You may notice that your default model in ChatGPT has been updated to GPT-5.1 this week. GPT-5.1 brings improvements across reasoning, instruction-following, and personalization (including personalities and Instant/Thinking modes). You should notice faster, more relevant responses and better behavior on mixed-complexity tasks.
[Add in details about accessing legacy models, if available]
To test it out, I recommend you:
- Try out some more complex strategic questions to see the reasoning power of GPT-5.1-Thinking.
- Experiment with the new model personalities by clicking on your Name > Personalization > Base Style and Tone
- Review any custom GPTs you have built, and test them with GPT-5.1. We recommend switching the Recommended Model ASAP, as these will automatically migrate in January 2026. See more about GPT-5.1 in the OpenAI Help Center, and blog Manage access to legacy models: While the default experience will be GPT-5.1, you can still manage access to legacy models for your team. See details about legacy model access in our Help Center.
Additional resources
- OpenAI Help Center
- Introducing GPT-5.1 blog
Table Of Contents
Popular
Dive in