# \[Solved\] Current OpenAI integration is legacy and is being deprecated by OpenAI
**URL:** https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457
**Category:** Questions about Thunkable X
**Created:** [January 5, 2024, 8:35pm UTC](https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457 "2024-01-05T20:35:03Z")
**Posts on this page:** 12
**Page:** 1
### Author:  [@george.prakashbn](https://community.thunkable.com/u/george.prakashbn)
#### Post date: [January 5, 2024, 8:35pm UTC](https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457/1 "2024-01-05T20:35:03Z")
HI Team
I got an email saying that on Jan 4th 2024 , OpenAi will deprecate / shut down all their old legacy models including text-davinci-003 . This is the model under the hood that the thunkable integration has to the old api documented here -[https://platform.openai.com/docs/api-reference/completions/create](https://platform.openai.com/docs/api-reference/completions/create)
Will this be fixed by Thunkable and will the tool be updated to the new api ? I’m presuming everyone’s who has used the OpenAi integration in thunkable would have received an email from OpenAi telling them this.
Looking forward to a solution. Thanks.
---
### Author:  [@emlee703](https://community.thunkable.com/u/emlee703)
#### Post date: [January 5, 2024, 9:47pm UTC](https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457/2 "2024-01-05T21:47:42Z")
Welcome to Thunkable @george.prakashbn!
I don’t use OpenAi in my Thunkable projects, however like you, I would guess that Thunkable would need to integrate a newer version.
The people that probably can help are, @matt_conroy and @ioannis
---
### Author:  [@matt\_conroy](https://community.thunkable.com/u/matt_conroy)
#### Post date: [January 5, 2024, 10:02pm UTC](https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457/3 "2024-01-05T22:02:47Z")
Thanks for flagging, I think this was originally announced back in July. I will check with the Product team and see what is in store.
---
### Author:  [@tatiang](https://community.thunkable.com/u/tatiang)
#### Post date: [January 6, 2024, 2:58am UTC](https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457/4 "2024-01-06T02:58:14Z")
From [GPT-4 API general availability and deprecation of older models in the Completions API](https://openai.com/blog/gpt-4-api-general-availability) (emphasis mine):
> **Developers using other older completion models (such as `text-davinci-003`) will need to manually upgrade their integration by January 4, 2024 by specifying `gpt-3.5-turbo-instruct` in the “model” parameter of their API requests.** `gpt-3.5-turbo-instruct` is an InstructGPT-style model, trained similarly to `text-davinci-003`. This new model is a drop-in replacement in the Completions API and will be available in the coming weeks for early testing.
---
### Author:  [@george.prakashbn](https://community.thunkable.com/u/george.prakashbn)
#### Post date: [January 7, 2024, 10:09am UTC](https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457/5 "2024-01-07T10:09:46Z")
thx @matt_conroy - please let me know when they plan on sorting this out.
@tatiang - are you saying I should be manually upgrading and passing in the model parameter? or meant for the Product team to upgrade their integration?
---
### Author:  [@mannankhanabdul](https://community.thunkable.com/u/mannankhanabdul)
#### Post date: [January 7, 2024, 2:31pm UTC](https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457/6 "2024-01-07T14:31:43Z")
As an alternative Gemini API is performing good. Posting the working solution by @tatiang
> [@Getting Started with Google Gemini API](https://community.thunkable.com/t/getting-started-with-google-gemini-api/2757535):
>
> Here are the blocks I’ve configured that provide a valid JSON response from the Google Gemini API. You will need your own API key. Here’s an example of part of the JSON response formatted in [https://codebeautify.org/jsonviewer:](https://codebeautify.org/jsonviewer:) Here’s an example of the blocks that will allow you to parse out the “text” property from that API response: If you are able to get a response but need more help parsing the JSON text, see my full tutorial here: [API JSON Tutorial (Video)](https://community.thunkable.com/t/api-json-tutorial-video/1140575).
Thanks
Abdul
---
### Author:  [@tatiang](https://community.thunkable.com/u/tatiang)
#### Post date: [January 7, 2024, 3:47pm UTC](https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457/7 "2024-01-07T15:47:07Z")
I guess both. Accessing ChatGPT via the Web API blocks in Thunkable gives you a lot more power and flexibility.
---
### Author:  [@george.prakashbn](https://community.thunkable.com/u/george.prakashbn)
#### Post date: [January 7, 2024, 6:12pm UTC](https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457/8 "2024-01-07T18:12:03Z")
@tatiang - Thx - specifying `gpt-3.5-turbo-instruct` in the “model” parameter helped fix the text completion. What do i do for Image generation ?
---
### Author:  [@tatiang](https://community.thunkable.com/u/tatiang)
#### Post date: [January 7, 2024, 7:24pm UTC](https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457/9 "2024-01-07T19:24:40Z")
I’m not sure. When I set up API access for ChatGPT they hadn’t released DALL-E integration yet. I used a separate API and then decided to go with the Stable Diffusion API instead.
> [@Chat AI & Image Generator (aka Synthi)](https://community.thunkable.com/t/chat-ai-image-generator-aka-synthi/2227603?page=2):
>
> Synthi Chat AI & Image Generator (work in progress) Overview Thanks to @ioannisroungeris/@ioannis posting [this](https://community.thunkable.com/t/open-ai-chatgpt/2174483) a month ago, I started my deep dive into AI’s chat and image generator features. I’ve put a lot of time into this project – before Thunkable [added blocks to help with all this](https://community.thunkable.com/t/openai-chatgpt-now-available-in-thunkable-with-our-new-integration/2209360) – and had to learn a lot about chat parameters, image generator prompts, and text-to-speech. I’m calling it Synthi for now. So what does it do? It’s a conversational chat bot and image generator with a magic pro…
---
### Author:  [@matt\_conroy](https://community.thunkable.com/u/matt_conroy)
#### Post date: [January 11, 2024, 3:00pm UTC](https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457/10 "2024-01-11T15:00:27Z")
@bschwartzsxc2 @george.prakashbn The default model has been updated to `gpt-3.5-turbo-instruct`
Please keep in mind that you may need to do a [hard refresh](https://docs.thunkable.com/getting-started/data-sources/data-sources#hard-refresh-your-browser)of your browser for the changes to take effect in your project. If you experienced any of these issues on the [Thunkable Live](https://thunkable.com/mobile) app, you will need to update to the latest version through the App Store and/or Google Play Store before any changes will occur. If your [downloaded or published app](https://docs.thunkable.com/publishing-apps/publish) is affected by any of these issues, you will need to re-download or re-publish your app for these changes to take effect.
---
### Author:  [@george.prakashbn](https://community.thunkable.com/u/george.prakashbn)
#### Post date: [January 11, 2024, 6:00pm UTC](https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457/11 "2024-01-11T18:00:52Z")
Excellent - thank you @matt_conroy .
Just as an FYI for anyone else who like me , had added in the model parameter in the request as a workaround. We have to remove that model parameter now . Keeping it in for some reason doesn’t work. Once I removed the parameter, it started working. And as a bonus - the image generation started working too!!
---
### Author:  [@matt\_conroy](https://community.thunkable.com/u/matt_conroy)
#### Post date: [January 12, 2024, 4:21pm UTC](https://community.thunkable.com/t/solved-current-openai-integration-is-legacy-and-is-being-deprecated-by-openai/2769457/12 "2024-01-12T16:21:21Z")