# 🤖 GPT-4o, the latest model from OpenAI, is now available **URL:** \ **Category:** General\ **Created:** [May 15, 2024, 10:34pm UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420 "2024-05-15T22:34:43Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![david](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/david/32/62831_2.png) [@david](https://community.glideapps.com/u/david)\ **Post date:** [May 15, 2024, 10:34pm UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/1 "2024-05-15T22:34:43Z")
In the `Generate Text` action, you’ll find a new `High Power v2` model, which is `GPT-4o` under the covers. It should be better in every way, and less expensive for processing large prompts. If you are using `Generate Text`, please give this new model a try and report what you find. We’re currently evaluating this model for use with the other `Glide AI` actions as well. We’ve also introduced `Image to Text v2`. Please give it a try and share your feedback. This is a huge leap forward from the previous version, in terms of vision and reasoning capabilities. We had a customer attempting to process photos of handwritten forms, and it simply did not work with the previous `Image to Text`. This new version completed the tasks perfectly on the first try. ---
**Author:** ![david](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/david/32/62831_2.png) [@david](https://community.glideapps.com/u/david)\ **Post date:** [May 15, 2024, 10:34pm UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/2 "2024-05-15T22:34:51Z")
---
**Author:** ![christian\_k](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/christian_k/32/49583_2.png) [@christian\_k](https://community.glideapps.com/u/christian_k)\ **Post date:** [May 16, 2024, 4:11am UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/3 "2024-05-16T04:11:01Z")
I was testing the “Complete chat” column and I can confirm that the new 4o model works just fine, is fast, and also costs less than 4. In this picture, you can see the costs of analysing a medium-long text through the API (around 4 pages in a document): I did it once with 4, and once (!) with 4o, and several times with 3.5-turbo during that day. ![Screenshot 2024-05-16 at 06.04.44](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/b/9/b90d1c74ca2dcb37dfc34ec467e754c0293fa662.png) Next thing I will test soon is the capability to analyse a picture, which they claim 4o can do. ---
**Author:** ![david](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/david/32/62831_2.png) [@david](https://community.glideapps.com/u/david)\ **Post date:** [May 17, 2024, 10:03pm UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/4 "2024-05-17T22:03:37Z")
**Update** : we’ve also released `Image to Text v2` ---
**Author:** ![AyS\_0908](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/ays_0908/32/27349_2.png) [@AyS\_0908](https://community.glideapps.com/u/AyS_0908)\ **Post date:** [May 18, 2024, 9:10am UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/5 "2024-05-18T09:10:56Z")
Did not work for me… in “Chat Completion” ![image](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/8/6/864cf38b20b7df1f33ace9419a3fa428907c5fc4.png) [edited] works with the model’s name in lower case: gpt-4o ---
**Author:** ![david](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/david/32/62831_2.png) [@david](https://community.glideapps.com/u/david)\ **Post date:** [May 18, 2024, 2:03pm UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/6 "2024-05-18T14:03:30Z")
The thread is about the Glide AI integration, not the OpenAI one. ---
**Author:** ![chanwise](https://avatars.discourse-cdn.com/v4/letter/c/f08c70/32.png) [@chanwise](https://community.glideapps.com/u/chanwise)\ **Post date:** [June 3, 2024, 2:33am UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/7 "2024-06-03T02:33:27Z")
I’m new to ChatGPT subscription but just signed up recently to test 4o and use the new model. So if I use it on their site, I’m getting up to date information but the model through Glide AI integration set to High Power v2 is only showing up to Oct 2023. I know according to their docs, it says training data up to Oct 2023, but unsure how that’s different than the 4o I’m using through their desktop app or site. ---
**Author:** ![ThinhDinh](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/thinhdinh/32/49_2.png) [@ThinhDinh](https://community.glideapps.com/u/ThinhDinh)\ **Post date:** [June 3, 2024, 3:27am UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/8 "2024-06-03T03:27:56Z")
> [@chanwise](#): > > I’m getting up to date information Can you specify if the web version uses “browsing” mode at any point? ---
**Author:** ![chanwise](https://avatars.discourse-cdn.com/v4/letter/c/f08c70/32.png) [@chanwise](https://community.glideapps.com/u/chanwise)\ **Post date:** [June 3, 2024, 3:42am UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/9 "2024-06-03T03:42:46Z")
I’m not sure how to check but I’m assuming it probably is since it’s getting info as of today ---
**Author:** ![chanwise](https://avatars.discourse-cdn.com/v4/letter/c/f08c70/32.png) [@chanwise](https://community.glideapps.com/u/chanwise)\ **Post date:** [June 3, 2024, 3:50am UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/10 "2024-06-03T03:50:56Z")
![image](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/8/d/8d43b574945db93259d362c477420cb18711cb94.jpeg) yep, got the answer. ---
**Author:** ![ThinhDinh](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/thinhdinh/32/49_2.png) [@ThinhDinh](https://community.glideapps.com/u/ThinhDinh)\ **Post date:** [June 3, 2024, 8:27am UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/11 "2024-06-03T08:27:39Z")
![image](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/f/f/ff828df1ea0e64fba20923177f4d19d13a635af6.png) Here’s how you would know if it used a search function. ---
**Author:** ![fk1214](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/fk1214/32/71058_2.png) [@fk1214](https://community.glideapps.com/u/fk1214)\ **Post date:** [June 3, 2024, 5:21pm UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/12 "2024-06-03T17:21:35Z")
Why did I see this as " 🤖 GPT-4o, the latest model from Glide, is now available" for a sec LMAO ---
**Author:** ![Martin\_B](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/martin_b/32/74360_2.png) [@Martin\_B](https://community.glideapps.com/u/Martin_B)\ **Post date:** [June 10, 2024, 2:15pm UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/13 "2024-06-10T14:15:26Z")
I didnt see this thread on time and posted on another one… But here is my questioning: > [@Open AI Integration - "Answer question about table" error message](https://community.glideapps.com/t/open-ai-integration-answer-question-about-table-error-message/66048/5): > > Hello, I use OPEN AI action… model: gpt-4o Works fine with 4096 tokens max length. But then when i set the actual context window from OPEN AI docs 128,000 tokens it doesn’t work. even if i set maximum answer length to 124000 to take into account my input 1355 tokens + buffer) Any suggestions? Is it a Glide limitation? If so, im ready to pay 2 updates to get the full use of OPEN AI Capacity… wink even if this double billing wouldn’t be fair as im paying also for my open AI account usag… > [@Open AI Integration - "Answer question about table" error message](https://community.glideapps.com/t/open-ai-integration-answer-question-about-table-error-message/66048/7): > > Thanks for answering. To simplify our conversation. maximum token window gpt-4o (128000) I request an answer length (124000) So there is enough for my system prompt + user prompt (1500+1500 = a total 3000 ) plus a buffer (1000 tokens). I confirm the action works with gpt-4o model selected in Glide, but with only 4096 tokens maximum. It should be 128.000 Any specialist? @grumowink Creator of excellent AI QUIZZ template worth trying… Merci No double billing please… Let us use OPEN AI action with maximum capacity.(token windows etc) From team plan maybe? else users only have access to Glide AI… I just saw that: ![Screenshot 2024-06-10 at 16.34.33](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/3/7/37c223976125c3ff14d44816362d4c74c8f7b8f6.png) Which would mean 96 updates (1,92$) to have one High power v2 request with max tokens (128000)… 🫣 ---
**Author:** ![ThinhDinh](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/thinhdinh/32/49_2.png) [@ThinhDinh](https://community.glideapps.com/u/ThinhDinh)\ **Post date:** [June 11, 2024, 11:32pm UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/14 "2024-06-11T23:32:20Z")
I’m just curious, how many use cases you would have that require 128,000 tokens? That’s a lot of words and to be honest if you generate, say 124,000 tokens (taking out your input and system prompt), 2 dollars is not a crazy price. 128k tokens means 93k words. I did a search, let’s say a page has 300 words. That makes it 310 pages of content. ![image](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/a/e/ae946b9fb0bccb16c44045fbb637b26303c3391d.png) ---
**Author:** ![Martin\_B](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/martin_b/32/74360_2.png) [@Martin\_B](https://community.glideapps.com/u/Martin_B)\ **Post date:** [June 12, 2024, 11:32am UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/15 "2024-06-12T11:32:35Z")
What can i say… you are actually right. Thanks and sorry. I hope this thread will help others though. > Now, i hope glide will allow to change from 4096 tokens to 128000 tokens (or any new max. On GLIDE AI and OPEN AI actions/columns. 🙏 ---
**Author:** ![ThinhDinh](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/thinhdinh/32/49_2.png) [@ThinhDinh](https://community.glideapps.com/u/ThinhDinh)\ **Post date:** [June 16, 2024, 10:36pm UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/16 "2024-06-16T22:36:07Z")
Hey Martin, I actually checked again today, and want to clarify something. ![image](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/b/0/b0b998704611f2c96e2c9878235af88db626c43c.jpeg) Whilst those models can have a maximum token window of 128k tokens, they have a limited output token. For gpt-4-0125-preview, that limit was 4096, so your question is valid. gpt-3.5 has this same limit stated on their website. On Microsoft’s website, gpt-4o is confirmed to have the same limit. Claude 3 as well. ![image](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/a/c/ac88d1d71c72663eb432cbb07082976d757289b8.png) ![image](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/b/b/bbe78b8da8bbc00f35f71a12fcb440cd837801ce.png) ![image](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/5/9/591a41776e477ae4b4f08467dc1f79206eea1f00.png) Gemini seems to have the most amongst the big models, for now. ![image](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/2/d/2d627eb0390dbe4dcdebd45ca38c3ea1641126ec.jpeg) ---
**Author:** ![Martin\_B](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/martin_b/32/74360_2.png) [@Martin\_B](https://community.glideapps.com/u/Martin_B)\ **Post date:** [June 17, 2024, 12:07pm UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/17 "2024-06-17T12:07:45Z")
Thanks Thinh, good catch. Im surprised Open ai didn’t mention the output of the model GPT4o like they did for others… But thanks to your investigation, it seems to be confirmed at 4096tokens. ---
**Author:** ![aledesousa](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/aledesousa/32/229_2.png) [@aledesousa](https://community.glideapps.com/u/aledesousa)\ **Post date:** [July 21, 2024, 3:22am UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/19 "2024-07-21T03:22:40Z")
OpenIA launched GPT 4o Mini, smarter, faster and cheaper than GPT 3.5. Will we see changes to the default Glide AI model? ---
**Author:** ![Jeff\_Hager](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/jeff_hager/32/43_2.png) [@Jeff\_Hager](https://community.glideapps.com/u/Jeff_Hager)\ **Post date:** [July 21, 2024, 11:43am UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/20 "2024-07-21T11:43:29Z")
> [@robot GPT-4o, the latest model from OpenAI, is now available](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420): > > In the Generate Text action, you’ll find a new High Power v2 model, which is GPT-4o under the covers. It should be better in every way, and less expensive for processing large prompts. If you are using Generate Text, please give this new model a try and report what you find. We’re currently evaluating this model for use with the other Glide AI actions as well. We’ve also introduced Image to Text v2. Please give it a try and share your feedback. This is a huge leap forward from the previous ver… ---
**Author:** ![ThinhDinh](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/thinhdinh/32/49_2.png) [@ThinhDinh](https://community.glideapps.com/u/ThinhDinh)\ **Post date:** [July 21, 2024, 2:31pm UTC](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420/21 "2024-07-21T14:31:02Z")
The thread you linked to is GPT-4o, OpenAI released a mini version of it which is less expensive. I hope it will get integrated maybe in the next 2 weeks. [Next page](https://community.glideapps.com/t/gpt-4o-the-latest-model-from-openai-is-now-available/73420.md?page=2)