{"id":9679,"date":"2025-04-25T12:45:52","date_gmt":"2025-04-25T16:45:52","guid":{"rendered":"https:\/\/blogs.swarthmore.edu\/its\/?p=9679"},"modified":"2025-04-25T12:45:52","modified_gmt":"2025-04-25T16:45:52","slug":"demystifying-the-names-of-the-chatgpt-models","status":"publish","type":"post","link":"https:\/\/blogs.swarthmore.edu\/its\/2025\/04\/25\/demystifying-the-names-of-the-chatgpt-models\/","title":{"rendered":"Demystifying the names of the ChatGPT models"},"content":{"rendered":"\n

When it comes to picking a GPT model, it’s not very clear-cut which model you should use. The naming conventions of the models is pretty confusing to new users. Here is a cheat sheet describing how ChatGPT names its models, and which ones you should be using for your task. (Or you can just jump to the TLDR<\/a>)<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Naming Convention<\/h2>\n\n\n\n

Each model starts with the model name, followed by its version number.<\/p>\n\n\n\n

Model Name<\/th>What to use it for<\/th>Examples<\/th><\/tr><\/thead>
GPT<\/td>General purpose<\/td>GPT<\/strong>-4.1,
GPT<\/strong>-4o,
GPT<\/strong>-3.5<\/td><\/tr>
o<\/td>Reasoning<\/td>o<\/strong>4, o<\/strong>3, o<\/strong>1<\/td><\/tr>
DALL-E<\/td>Image generation<\/td>DALL-E<\/strong> 2
DALL-E<\/strong> 3<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

Pro Tip<\/strong>: The o<\/strong> in GPT-4o<\/strong> stands for “omni”, which indicates it is multimodal (can handle text, vision, audio, etc…).

This should not<\/strong> be confused with the o<\/strong> models that are used for reasoning.<\/p><\/blockquote>\n\n\n\n

Optionally, models may have a suffix.<\/p>\n\n\n\n

Suffix<\/th>Meaning<\/th><\/tr><\/thead>
mini<\/td>Faster and less cost at the cost of precision<\/td><\/tr>
nano<\/td>Even faster and even more cost efficient than (at an even greater loss of precision though)<\/td><\/tr>
Turbo<\/td>Fine tuned models (often with larger context sizes)<\/td><\/tr>
Preview<\/td>The newest models. You can think of these are betas. Newer does not always mean they perform better!<\/strong><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

You may also notice that some models have a 16k<\/strong> (or similar number + k<\/strong>). This represents the model’s context window.<\/p>\n\n\n\n

Some older models also have a date appended to them, representing when it was trained (ie. -0613<\/strong> indicates the model was trained on June 13).<\/p>\n\n\n\n

TLDR<\/h2>\n\n\n\n

For general purpose stuff, you probably want 4o-mini<\/strong> (or GPT-4o if you need the intelligence boost from it).<\/p>\n\n\n\n

For vibe coding, you probably want o3-mini<\/strong> or o3<\/strong>.<\/p>\n\n\n\n

OpenAI has also published a model comparison page<\/a> that breaks all of this down even more.<\/p>\n","protected":false},"excerpt":{"rendered":"

When it comes to picking a GPT model, it’s not very clear-cut which model you should use. The naming conventions of the models is pretty confusing to new users. Here is a cheat sheet describing how ChatGPT names its models, … Continue reading Demystifying the names of the ChatGPT models<\/span><\/a><\/p>\n","protected":false},"author":70,"featured_media":9683,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[2,436,500],"tags":[90],"class_list":{"0":"post-9679","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","6":"hentry","7":"category-academic-technology","8":"category-artificial-intelligence-2","9":"category-chatgpt","10":"tag-featured","12":"fallback-thumbnail"},"jetpack_featured_media_url":"https:\/\/blogs.swarthmore.edu\/its\/wp-content\/uploads\/2025\/04\/ChatGPT-Image-Apr-25-2025-at-12_39_56-PM.png","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/ph2nPL-2w7","_links":{"self":[{"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/posts\/9679","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/users\/70"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/comments?post=9679"}],"version-history":[{"count":2,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/posts\/9679\/revisions"}],"predecessor-version":[{"id":9682,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/posts\/9679\/revisions\/9682"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/media\/9683"}],"wp:attachment":[{"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/media?parent=9679"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/categories?post=9679"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/tags?post=9679"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}