# Not able to access fine tuned model using API **URL:** \ **Category:** API\ **Created:** [August 13, 2024, 6:09am UTC](https://community.openai.com/t/not-able-to-access-fine-tuned-model-using-api/905021 "2024-08-13T06:09:56Z")\ **Posts on this page:** 10\ **Page:** 1
**Author:** ![jitulvc](https://avatars.discourse-cdn.com/v4/letter/j/cdc98d/32.png) [@jitulvc](https://community.openai.com/u/jitulvc)\ **Post date:** [August 13, 2024, 6:09am UTC](https://community.openai.com/t/not-able-to-access-fine-tuned-model-using-api/905021/1 "2024-08-13T06:09:56Z")
Hi, after I successfully fine tuned model, I am not able to access it via API call. gptclient.chat.completions.create(model=modelid, messages=message). The error message is as the follow. The model `ft:gpt-3.5-turbo-0125:personal::9vebcwxS` does not exist or you do not have access to it. I only have default project and not able to nail down the problem. ---
**Author:** ![dignity\_for\_all](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/dignity_for_all/32/300058_2.png) [@dignity\_for\_all](https://community.openai.com/u/dignity_for_all)\ **Post date:** [August 13, 2024, 8:20am UTC](https://community.openai.com/t/not-able-to-access-fine-tuned-model-using-api/905021/2 "2024-08-13T08:20:26Z")
Welcome to the community! As the fine-tuned model name says Personal, you have a fine-tuned model created with a Personal account. If you only have a Personal account, this is normal. Possible points to consider are: - The fine-tuned model name is incorrect. - You are not using the API key created in your Personal account. Please make sure that you are using the exact API key that you created during the fine-tuning process, and verify that the name of the tuned model is correct using the following method. If you are using Python: ```auto from openai import OpenAI client = OpenAI() client.fine_tuning.jobs.list() ``` If you are using Node.js: ```auto import OpenAI from "openai"; const openai = new OpenAI(); async function main() { const list = await openai.fineTuning.jobs.list(); for await (const fineTune of list) { console.log(fineTune); } } main(); ``` This will get the exact name of the fine-tuning model. ---
**Author:** ![jitulvc](https://avatars.discourse-cdn.com/v4/letter/j/cdc98d/32.png) [@jitulvc](https://community.openai.com/u/jitulvc)\ **Post date:** [August 13, 2024, 9:24am UTC](https://community.openai.com/t/not-able-to-access-fine-tuned-model-using-api/905021/3 "2024-08-13T09:24:51Z")
The funny part is, all my previously fine tuned models, I am able to access via API. Only the models which I fine tuned today are giving me this error. I was using API key created in my personal account all along, but today after facing the above problem, I created a new key at the project level (default project) and used that key to fine tune the next model. But, the problem persists. So, not able to figure out exact cause yet. ---
**Author:** ![dignity\_for\_all](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/dignity_for_all/32/300058_2.png) [@dignity\_for\_all](https://community.openai.com/u/dignity_for_all)\ **Post date:** [August 13, 2024, 9:49am UTC](https://community.openai.com/t/not-able-to-access-fine-tuned-model-using-api/905021/4 "2024-08-13T09:49:44Z")
I see, although the official status page shows All Systems Operational, but maybe there is some kind of system failure. Unfortunately, OpenAI staff is not here, so there is no one able to solve the problem directly, but it might be helpful to report the problem via the help widget. I am sorry that this is all I can say, but I hope that your problem will be solved as soon as possible. ---
**Author:** ![Kamen](https://avatars.discourse-cdn.com/v4/letter/k/ee59a6/32.png) [@Kamen](https://community.openai.com/u/Kamen)\ **Post date:** [August 13, 2024, 10:23am UTC](https://community.openai.com/t/not-able-to-access-fine-tuned-model-using-api/905021/5 "2024-08-13T10:23:26Z")
I have the same problem. I’ve also noticed that after the fine-tune is ready there’s a check of model’s answers if they comply with the OpenAI policies: “Evaluating model against our usage policies before enabling.” - it takes years. Anyway, after the check is done and I try to access the model via API it is not available. FT models fine tuned today are not available for further fine tuning and even in the playground. ---
**Author:** ![jitulvc](https://avatars.discourse-cdn.com/v4/letter/j/cdc98d/32.png) [@jitulvc](https://community.openai.com/u/jitulvc)\ **Post date:** [August 13, 2024, 1:48pm UTC](https://community.openai.com/t/not-able-to-access-fine-tuned-model-using-api/905021/6 "2024-08-13T13:48:51Z")
How do we report a problem via the help widget? ---
**Author:** ![mirrorerror2091](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/mirrorerror2091/32/146303_2.png) [@mirrorerror2091](https://community.openai.com/u/mirrorerror2091)\ **Post date:** [August 13, 2024, 6:38pm UTC](https://community.openai.com/t/not-able-to-access-fine-tuned-model-using-api/905021/7 "2024-08-13T18:38:50Z")
I encountered the same problem, when trying to call a fine tuned model I get an error “The model `ft:davinci-002:personal:: ***** ` does not exist or you do not have access to it.” When calling a model fin tuned a few days ago, everything works, so the problem is definitely not in the correctness of the access token being transmitted The model name was also checked many times… ---
**Author:** ![silvio.goncalves](https://avatars.discourse-cdn.com/v4/letter/s/d07c76/32.png) [@silvio.goncalves](https://community.openai.com/u/silvio.goncalves)\ **Post date:** [August 14, 2024, 8:47pm UTC](https://community.openai.com/t/not-able-to-access-fine-tuned-model-using-api/905021/8 "2024-08-14T20:47:31Z")
Hi! model=“gpt-3.5-turbo-1106” or “gpt-4o-mini-2024-07-18” works for me. ---
**Author:** ![sar](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/sar/32/444383_2.png) [@sar](https://community.openai.com/u/sar)\ **Post date:** [August 16, 2024, 2:36am UTC](https://community.openai.com/t/not-able-to-access-fine-tuned-model-using-api/905021/9 "2024-08-16T02:36:49Z")
Seems like a bug. Finetuning 4o-mini takes X but models have a unusual tendency of getting stuck in _Evaluating model against our usage policies before enabling._ state taking almost 2X longer. More finetuned input tokens, multiplies this lag. ---
**Author:** ![bergamo86](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/bergamo86/32/454702_2.png) [@bergamo86](https://community.openai.com/u/bergamo86)\ **Post date:** [December 21, 2024, 12:12am UTC](https://community.openai.com/t/not-able-to-access-fine-tuned-model-using-api/905021/10 "2024-12-21T00:12:44Z")
{ “error”: { “message”: “Project `proj_PZUGVjOPVk8iSctnmcbkoIwV` does not have access to model `ft:gpt-4o-mini-2024-07-18:neurok-ai::Agh159Aw`”, “type”: “invalid\_request\_error”, “param”: null, “code”: “model\_not\_found” } } i have the same problem… i try differents api keys and not happen. i not activate in openai dashboard ( not make sense because im using api)