OpenAI models: Every model and what it's best for

Keeping track of all the new AI models getting released at the moment is practically a full-time job. I would know: I've been writing about them for the past few years, and it feels like every time I publish an article, another new model drops. OpenAI is one of the worst offenders (or prolific innovators), and things aren't helped by how confusing all the OpenAI model names are. 

So, let's try to simplify things: consider this your complete guide to all of OpenAI's major models. We'll look at what each one is good for, how much they cost, and how to make the most of them in your work. 

But first, I have to apologize for the crimes against consistent naming conventions, capitalization, and hyphenation we're all going to have to endure. GPT-5 nano, gpt-oss-120b, and GPT Image 1 are three of OpenAI's latest models. Hang in there.

Table of contents:

.css-6hywhk{color:#403f3e;list-style:disc;margin-left:10px;padding-left:10px;font-family:var(–zds-typography-base, “Inter”, Helvetica, arial, sans-serif);font-size:16px;line-height:24px;font-weight:400;}@media (min-width: 660px){.css-6hywhk{font-family:var(–zds-typography-base, “Inter”, Helvetica, arial, sans-serif);font-size:18px;line-height:31px;font-weight:400;}}

.css-oiqntf{display:-webkit-box;display:-webkit-list-item;display:-ms-list-itembox;display:list-item;}.css-oiqntf::marker{color:#403f3e;}

• .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}Why are there so many OpenAI models?

• .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}Major OpenAI models

• .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}Legacy OpenAI models

• .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}How to choose the right OpenAI model

• .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}Automate OpenAI models

.css-1ilpmu8{color:#2d2e2e;font-family:var(–zds-typography-heading, “Degular”, Helvetica, arial, sans-serif);font-size:34px;line-height:40px;font-weight:600;letter-spacing:1px;}

Why are there so many OpenAI models?

OpenAI is one of the most important AI companies. Its .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}ChatGPT chatbot and .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}DALL·E 2 image generator essentially kickstarted the current AI boom. Over the past few years, it's continued to develop .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}large language models, .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}multimodal models, and .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}text-to-image models.

OpenAI is moving fast. As the technology advances, new models have come out, and we've naturally been left with an extensive list—including some legacy models.

.css-edievn{background-color:#f7f5f2;padding:15px;}@media (min-width: 660px){.css-edievn{padding:20px;}}

OpenAI models at a glance

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-5.1

.css-bmqgnp{color:#2d2e2e;font-family:var(–zds-typography-base, “Inter”, Helvetica, arial, sans-serif);font-size:24px;line-height:30px;font-weight:700;}

Best OpenAI model for advanced reasoning and logic

GPT-5.1 is OpenAI's flagship reasoning model and one of the most powerful AI models available right now. It's the successor to GPT-5.

Reasoning models like GPT-5.1 are best for logical, technical, and scientific tasks. With GPT-5.1, you set a reasoning effort—minimal, low, medium, or high—that determines how many tokens it uses to work through a problem. It also has a "none" effort that prioritizes speed.

If you need the most powerful model OpenAI has for generating computer code, analyzing text documents and images, or solving complex puzzles, GPT-5.1 is the one to use. But because reasoning models use additional resources to work through problems, they're more expensive for tasks that don't require advanced reasoning.

• GPT-5.1 inputs: Text, images

• GPT-5.1 outputs: Text

• GPT-5.1 context window: 400,000 tokens

• GPT-5.1 input pricing: $1.25/M tokens

• GPT-5.1 output pricing: $10/M tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-5

Superseded by GPT-5.1

GPT-5 was OpenAI's flagship reasoning model. It has now been superseded by GPT-5.1, which has improved speed and coding performance. While GPT-5 is still available through the API, you should update any tools you've built with it to GPT-5.1.

• GPT-5 inputs: Text, images

• GPT-5 outputs: Text

• GPT-5 context window: 400,000 tokens

• GPT-5 input pricing: $1.25/M tokens

• GPT-5 output pricing: $10/M tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-5 mini

Best OpenAI model for affordable reasoning and logic

GPT-5 mini is a faster and more affordable alternative to GPT-5. For well-defined or chatbot responses, it offers a great balance between power and performance.  

Like GPT-5, you have to set a reasoning effort with GPT-5 mini. The lower the reasoning effort, the faster and more affordable it will be. 

• GPT-5 mini inputs: Text, images

• GPT-5 mini outputs: Text

• GPT-5 mini context window: 400,000 tokens

• GPT-5 mini input pricing: $0.25/M tokens

• GPT-5 mini output pricing: $2/M tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-5 nano

Best OpenAI model for very affordable reasoning and logic

GPT-5 nano is OpenAI's fastest and most affordable reasoning model. It excels at tasks like summarization and classification. Like GPT-5 and GPT-5 mini, you have to set a reasoning effort with GPT-5 nano. 

• GPT-5 nano inputs: Text, images

• GPT-5 nano outputs: Text

• GPT-5 nano context window: 400,000 tokens

• GPT-5 nano input pricing: $0.05/M tokens

• GPT-5 nano output pricing: $0.40/M tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-5.1 Chat

Best OpenAI chat model (kind of)

GPT-5.1 Chat is the version of GPT-5.1 that's used for reasoning in ChatGPT. It's available through the API, but OpenAI recommends using GPT-5.1, GPT-4.1, or some other specialized model in most situations. It supersedes GPT-5 Chat.

• GPT-5.1 Chat inputs: Text, images

• GPT-5.1 Chat outputs: Text

• GPT-5.1 Chat context window: 128,000 tokens

• GPT-5.1 Chat input pricing: $1.25/M tokens

• GPT-5.1 Chat output pricing: $10/M tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-5.1 Codex

Best OpenAI model for long-running and agentic coding

GPT-5.1 Codex is a version of GPT-5.1 that's designed for agentic coding tasks in tools like Codex, Cursor, and Replit. It's best for complex and long-running coding tasks, like creating new functions and features and making major code base changes. 

• GPT-5.1 Codex inputs: Text, images

• GPT-5.1 Codex outputs: Text

• GPT-5.1 Codex context window: 400,000 tokens

• GPT-5.1 Codex input pricing: $1.25/M tokens

• GPT-5.1 Codex output pricing: $10/M tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-5.1 Codex mini

Best OpenAI model for cost-efficient coding

GPT-5.1 Codex mini is a version of GPT-5.1 Codex that's faster and more cost efficient, though less capable. It's optimized for making fast and affordable edits in tools like Codex, Cursor, and Replit. 

• GPT-5.1 Codex inputs: Text, images

• GPT-5.1 Codex outputs: Text

• GPT-5.1 Codex context window: 400,000 tokens

• GPT-5.1 Codex input pricing: $0.25/M tokens

• GPT-5.1 Codex output pricing: $2/M tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-4.1

Best OpenAI model for complex tasks that don't require advanced reasoning

GPT-4.1 is OpenAI's smartest non-reasoning multimodal LLM.

It's best to consider GPT-4.1 the ultimate Swiss Army knife of OpenAI's models. While there's very little it can't do, there are some situations where another model might be more appropriate. For example, a dedicated .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}reasoning model will perform better on multi-step tasks like code generation, while a .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}smaller cost-optimized model will offer better value for basic text generation. 

• GPT-4.1 inputs: Text, images

• GPT-4.1 outputs: Text

• GPT-4.1 context window: 1,047,576 tokens

• GPT-4.1 input pricing: $2/M tokens

• GPT-4.1 output pricing: $8/M tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-4.1 mini

Best OpenAI model for balancing power, performance, and affordability

GPT-4.1 mini is a fast and affordable general-purpose AI model. In benchmarks, it performs almost as well as GPT-4.1 but at ⅕th the price. If you aren't sure which model to use, GPT-4.1 mini is probably the sensible starting point. Unless you know you need the extra power of GPT-4.1 or are concerned about cost optimization, it's a very strong option. 

• GPT-4.1 mini inputs: Text, images

• GPT-4.1 mini outputs: Text

• GPT-4.1 mini context window: 1,047,576 tokens

• GPT-4.1 mini input pricing: $0.40/M tokens

• GPT-4.1 mini output pricing: $1.60/M tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-4.1 nano

Best OpenAI model for speed and price

GPT-4.1 nano is the smallest GPT-4.1 model available. As a result, it's the fastest and cheapest model—though it isn't as powerful as GPT-4.1 or GPT-4.1 mini. It's the model to use for simple tasks, or when you need to prioritize speed and cost-effectiveness. 

• GPT-4.1 nano inputs: Text, images

• GPT-4.1 nano outputs: Text

• GPT-4.1 nano context window: 1,047,576 tokens

• GPT-4.1 nano input pricing: $0.10/M tokens

• GPT-4.1 nano output pricing: $1.40/M tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-4o

Best OpenAI model for multimodality

While a specially trained version of GPT-4o can still run in ChatGPT (though it's deemed a legacy model by OpenAI), it's largely been replaced by the newer, more powerful, and more affordable GPT-4.1 model in the API. But GPT-4o still has one key API feature that its successor lacks: .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-4o Audio supports audio inputs and outputs. It can transcribe audio into text or reply with speech.

• GPT-4o inputs: Text, audio, images

• GPT-4o outputs: Text, audio

• GPT-4o context window: 128,000 tokens

• GPT-4o input pricing: $2.50/M tokens for text; $40/M tokens for audio

• GPT-4o output pricing: $10/M tokens for text; $80/M tokens for audio

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-4o mini

Best OpenAI model for multimodality on a budget

Like GPT-4o, GPT-4o mini has been replaced by the more affordable and powerful GPT-4.1 mini in the API. Similarly, .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT-4o mini Audio offers audio inputs and outputs for ¼th the cost of GPT-4o Audio. For developers that need an audio model but are cost constrained, it's the best option.

• GPT-4o mini inputs: Text, images, audio

• GPT-4o mini outputs: Text, audio

• GPT-4o mini context window: 128,000 tokens

• GPT-4o mini input pricing: $0.15/M tokens for text; $10/M tokens for audio

• GPT-4o mini output pricing: $0.60/M tokens for text; $20/M tokens for audio

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}gpt-oss-120b

Best open weight OpenAI model

gpt-oss-120b is OpenAI's most powerful open weight model, and it's the most powerful open model that can run on a single H100 GPU. It's released under an Apache 2.0 license, so you can download it and run it on your own server or choose from any third-party inference provider. You can also fine-tune the model to suit your needs. This is big for OpenAI, which historically, has only released proprietary models.

gpt-oss-120b has 117 billion parameters. It uses a mixture-of-experts architecture, so only 5.1 billion parameters are active at once. 

• gpt-oss-120b inputs: Text

• gpt-oss-120b outputs: Text

• gpt-oss-120b context window: 131,072 tokens

• gpt-oss-120b input pricing: Varies by provider

• gpt-oss-120b output pricing: Varies by provider

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}gpt-oss-20b

Best medium open weight OpenAI model

gpt-oss-20b is OpenAI's medium open weight model. It's designed to run locally and can even run on a sufficiently powerful laptop. Like gpt-oss-120b, it's released under an Apache 2.0 license, so you can download it yourself or choose from any third-party inference provider, and you can fine-tune the model to suit your needs. 

gpt-oss-20b has 21 billion parameters. It uses a mixture-of-experts architecture so only 3.6 billion parameters are active at once. 

• gpt-oss-120b inputs: Text

• gpt-oss-120b outputs: Text

• gpt-oss-120b context window: 131,072 tokens

• gpt-oss-120b input pricing: Varies by provider

• gpt-oss-120b output pricing: Varies by provider

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}o3

Superseded by GPT-5

o3 was OpenAI's most powerful reasoning model, but it has now been superseded by GPT-5. It's still available, at least for the time being, but you probably shouldn't choose to use it.

• OpenAI o3 inputs: Text, images

• OpenAI o3 outputs: Text

• OpenAI o3 context window: 200,000 tokens

• OpenAI o3 input pricing: $2/M tokens

• OpenAI o3 output pricing: $8/M tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}o3-pro

Best OpenAI model for really advanced reasoning and logic

o3-pro is the same underlying model as o3, but it's allowed to reason for more time to provide more reliable responses. It hasn't yet been officially superseded by GPT-5. OpenAI claims that o3-pro consistently outperformed o3 in head-to-head tests, so in some edge cases, it may still be the best model available. Otherwise, the performance gains may not be worth the price premium.

• OpenAI o3-pro inputs: Text, images

• OpenAI o3-pro outputs: Text

• OpenAI o3-pro context window: 200,000 tokens

• OpenAI o3-pro input pricing: $20/M tokens

• OpenAI o3-pro output pricing: $80/M tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}o4-mini

Superseded by GPT-5 mini

o4-mini was OpenAI's most powerful small reasoning model until the release of GPT-5 mini. It's still available, at least for now, but you should probably use GPT-5 mini instead.

• OpenAI o4-mini inputs: Text, images

• OpenAI o4-mini outputs: Text

• OpenAI o4-mini context window: 200,000 tokens

• OpenAI o4-mini input pricing: $1.10/M tokens

• OpenAI o4-mini output pricing: $4.40/M tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}Whisper

Best OpenAI model for affordable audio transcription

Whisper is an older audio transcription and translation model. While GPT-4o is far more powerful, at just $0.006 per minute of audio transcribed or translated, Whisper is a solid budget option for low-stakes audio services. 

• Whisper inputs: Text, images

• Whisper outputs: Text

• Whisper input pricing: $0.006/minute

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}GPT Image 1

Best OpenAI model for generating images

GPT Image 1 is the successor to OpenAI's .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}DALL·E image models, and it's one of the best text-to-image models available.

OpenAI's .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}pricing for image models is quite complicated because images are converted into tokens based on their size and quality. It currently costs $0.011 to generate a 1024 x 1024 low-quality image and $0.167 to generate a 1024 x 1024 high-quality image.

• GPT Image 1 inputs: Text, images

• GPT Image 1 outputs: Images

• GPT Image 1 input pricing: $5/M text tokens; $10/M image tokens

• GPT Image 1 output pricing: $40/M image tokens

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}Sora 2

Best OpenAI model for generating video

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}Sora 2 is OpenAI's flagship video generation model. It can take a combination of text prompts, still images, and videos, and generate a video and audio clip based on all that. Sora 2 and Sora 2 Pro are available through the API. Sora 2 Pro creates higher quality and resolution video but takes longer to render. 

• Sora 2 inputs: Text, images, videos

• Sora 2 outputs: Videos

• Sora 2 pricing: $0.10/second for 720p video; Pro: $0.30/second for 720p video and $0.50/second for full HD video

.css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}Sora 1

Best OpenAI model for generating video through an app

Sora 1 powers OpenAI's Sora web app and mobile app. It isn't available as an API.

Free users can generate six watermarked 10-second videos in 720p resolution per day, while ChatGPT Plus subscribers have a higher usage limit. ChatGPT Pro subscribers can generate un-watermarked 20-second videos in 1080p resolution.

• Sora inputs: Text, images, videos

• Sora outputs: Videos

• Sora pricing: Available free, as part of ChatGPT Plus ($20/month), and ChatGPT Pro ($200/month)

Legacy OpenAI models

OpenAI has developed and deprecated dozens of models over the past few years. Here are some of the major models that are no longer supported, actively used, or state-of-the-art:

• o1

• o1-pro

• GPT-4.5

• GPT-4

• GPT-3.5 Turbo

• GPT-3

• DALL·E 3

• DALL·E 2

How to choose the right OpenAI model

OpenAI has lots of models, but they each serve a purpose. GPT-5.1 and GPT-4.1 are the top reasoning and non-reasoning models, respectively, with the various mini and nano versions offering a different balance between price, performance, and speed. There's certainly a lot of overlap between the different models' abilities, especially when you take into account older models that haven't yet been replaced. But in general, one should strike you as the best balance between power, price, and ongoing development. 

OpenAI keeps releasing new models, changing pricing, and otherwise mixing things up. I'll do my best to keep this list as current and accurate as possible in the meantime.

Automate OpenAI models

All the OpenAI models are the most helpful when they're part of your existing workflow. With .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}Zapier's ChatGPT integration, you can use OpenAI's state-of-the-art models to automate everything from .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}intelligent sales outreach to .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}content generation to .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}customer support. This means doing things like automatically identifying opportunities in your CRM, summarizing business information, and prioritizing your workflow—using all the apps already in your tech stack.

Learn more about .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}how to automate OpenAI models with Zapier, or get started with one of these pre-made templates.

.css-1bxgpon-EmbeddedButton{width:100%;max-width:1170px;padding:20px 0;text-align:center;}

Related reading:

• .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}How to create a custom GPT: A beginner's guide

• .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}What are Claude computer use and ChatGPT Operator?

• .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}What is ChatGPT deep research?

• .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}What is mixture of experts in AI?

• .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}What is AI orchestration? A guide to intelligent systems

• .css-19a5n3-Link{all:unset;box-sizing:border-box;-webkit-text-decoration:underline;text-decoration:underline;cursor:pointer;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;outline-offset:1px;-webkit-text-fill-color:currentColor;outline:1px solid transparent;}.css-19a5n3-Link[data-color=’ocean’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’ocean’]:hover{outline-color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’ocean’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’white’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’white’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’white’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’primary’]{color:var(–zds-text-link, #3d4592);}.css-19a5n3-Link[data-color=’primary’]:hover{color:var(–zds-text-link-hover, #2b2358);}.css-19a5n3-Link[data-color=’primary’]:focus{color:var(–zds-text-link-hover, #3d4592);outline-color:var(–zds-text-link-hover, #3d4592);}.css-19a5n3-Link[data-color=’secondary’]{color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-color=’secondary’]:hover{color:var(–zds-gray-warm-5, #a8a5a0);}.css-19a5n3-Link[data-color=’secondary’]:focus{color:var(–zds-brand-almost-white, #fffdf9);outline-color:var(–zds-brand-almost-white, #fffdf9);}.css-19a5n3-Link[data-weight=’inherit’]{font-weight:inherit;}.css-19a5n3-Link[data-weight=’normal’]{font-weight:400;}.css-19a5n3-Link[data-weight=’bold’]{font-weight:700;}What is gpt-oss?

This article was originally published in May 2025. The most recent update was in December 2025.