# GPT 5.2 not working with reusable prompts in responses api **URL:** \ **Category:** Bugs\ **Created:** [December 12, 2025, 12:16pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113 "2025-12-12T12:16:35Z")\ **Posts on this page:** 17\ **Page:** 1
**Author:** ![or4](https://avatars.discourse-cdn.com/v4/letter/o/59ef9b/32.png) [@or4](https://community.openai.com/u/or4)\ **Post date:** [December 12, 2025, 12:16pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/1 "2025-12-12T12:16:35Z")
Hi all, I use the reusable prompts feature quite extensively and as I usually do when a new model comes out I updated the prompt to use GPT-5.2. However while this works in openai’s developer platform on our client end we get: Uh-oh! There was an issue with the response. Error: 400, message=‘Bad Request’, url=‘[https://api.openai.com/v1/responses](https://api.openai.com/v1/responses)’ Switching the model back to 5.1 fixes this immediately. I have tried similarly creating a new prompt with gpt-5.2 and get the same error. ---
**Author:** ![joeygennari](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/joeygennari/32/707786_2.png) [@joeygennari](https://community.openai.com/u/joeygennari)\ **Post date:** [December 12, 2025, 1:15pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/2 "2025-12-12T13:15:42Z")
I’m seeing the same. ```auto "error": { "message": "Unsupported parameter: 'top_p' is not supported with this model.", "type": "invalid_request_error", "param": "top_p", "code": null } ``` ---
**Author:** ![Francisco\_Macedo](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/francisco_macedo/32/707838_2.png) [@Francisco\_Macedo](https://community.openai.com/u/Francisco_Macedo)\ **Post date:** [December 12, 2025, 5:25pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/3 "2025-12-12T17:25:01Z")
I’m also seeing the same. And this is now happening with any model. ”HTTP 400 BadRequest: Unsupported parameter: ‘top\_p’ is not supported with this model.” ---
**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\ **Post date:** [December 12, 2025, 5:39pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/4 "2025-12-12T17:39:56Z")
The failing seems to be the Responses API refusing a parameter that should be accepted if a default of 1, as has been constant and consistent, as there are many “defaults” of parameters not supported but which will pass and be echoed as “medium”, `[]`, etc. GPT-5.2 actually does support temperature and top\_p - when using the default reasoning effort of “none”. Otherwise, such high temperature as this not constrained by first passing top “p” probability distribution would rapidly descend into textual madness (as seen below on Chat Completions). You’ll get an error if attempting non-default sampling parameters with higher reasoning settings, and that is the validation that must continue on this model, and top\_p must be allowed to remove more of a tail of the worst predictions. ![image](https://us1.discourse-cdn.com/openai1/original/4X/0/9/b/09b3d264a6b2d1cdcd815012ad5431cd988eb27c.png) ## Action needed by OpenAI - tolerate top\_p always on Responses - validate on sampling values in combination with “none” reasoning - provide “prompts” UI presentation for configuring all parameters within all accepted ranges, and store to the actual prompt object. - Provide real create, update, retrieve, list, delete API methods by developer API key, so I don’t have to warn every single inquiry against _ever_ using this platform lock-in. ---
**Author:** ![sps](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/sps/32/7736_2.png) [@sps](https://community.openai.com/u/sps)\ **Post date:** [December 12, 2025, 6:02pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/5 "2025-12-12T18:02:05Z")
Hi everyone, In my testing, I was able to successfully use the passed `prompt` param with the `gpt-5.2` model. If you’re still running into issues, please let me know the steps to reproduce them. Regarding the `"top_p"` error, this is explained in the [migration guidance](https://platform.openai.com/docs/guides/latest-model#migration-guidance) docs: > ### [GPT-5.2 parameter compatibility](https://platform.openai.com/docs/guides/latest-model#gpt-5-2-parameter-compatibility) > > The following parameters are **only supported** when using GPT-5.2 with reasoning effort set to `none`: > > - `temperature` > - `top_p` > - `logprobs` > > Requests to GPT-5.2 or GPT-5.1 with any other reasoning effort setting, or to older GPT-5 models (e.g., `gpt-5`, `gpt-5-mini`, `gpt-5-nano`) that include these fields will raise an error. ---
**Author:** ![pedobi7](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/pedobi7/32/150146_2.png) [@pedobi7](https://community.openai.com/u/pedobi7)\ **Post date:** [December 12, 2025, 6:14pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/6 "2025-12-12T18:14:49Z")
There is a bug in ResponsesApi. I don’t send top\_p in payload, but error is the result. ---
**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\ **Post date:** [December 12, 2025, 6:23pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/7 "2025-12-12T18:23:16Z")
> [@sps](#): > > Regarding the `"top_p"` error, Regarding the top-p error, the symptom is indicative of - API validation not accepting it at all, when it should be accepting int(1) in all cases - Prompts sending a value that does not validate. One can use developer tools-\>network, and observe the returned prompts object that is echoed back to the prompts playground when saving. You can expect that these are parameters that will run against the model. Further, if a bad value was being placed by prompts that a model won’t run, a runtime correction of sending `"top_p":1` yourself should be a mitgation on Responses. * * * Replication? I’m not currently in the mood to run diagnosis API calls against endpoint methods where I have already predicted and avoided pain points. ---
**Author:** ![sps](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/sps/32/7736_2.png) [@sps](https://community.openai.com/u/sps)\ **Post date:** [December 12, 2025, 7:35pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/8 "2025-12-12T19:35:56Z")
## UPDATE: After further testing with a new prompt created for `gpt-5.1` I was able to reproduce this issue by passing that same prompt with Responses API call with model set to `gpt-5.2`. Sharing with the team now. ---
**Author:** ![pedobi7](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/pedobi7/32/150146_2.png) [@pedobi7](https://community.openai.com/u/pedobi7)\ **Post date:** [December 15, 2025, 11:10am UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/9 "2025-12-15T11:10:22Z")
Is there any update or solution? ---
**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\ **Post date:** [December 15, 2025, 12:05pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/10 "2025-12-15T12:05:54Z")
Replication of issue: Create a new “prompt” from scratch, using “gpt-5.2”. Doing so does not send a `top_p` parameter when creating a prompt, but the prompt object returned has a `top_p:1.0`. This is also echoed in the successful use of the prompt ID. _WHEN reasoning.effort is “none”_. However, upgrade that same prompt ID with reasoning.effort:medium, the same top\_p is echoed in the object from the platform site’s API call (that you cannot make yourself with API key). Then: `Error code: 400 - {'error': {'message': "Unsupported parameter: 'top_p' is not supported with this model.", 'type': 'invalid_request_error', 'param': 'top_p', 'code': None}}` I never had a model other than GPT-5.2 in that particular brand new prompt ID, still failure. The workaround? > Pass `top_p:0.98` in the API call you make Yes, despite the error message text and unexpected malfunction in conjunction with prompts, you must disobey the error’s information. The reasoning mode of gpt-5.2 will accept its own default of `0.98` as a prompt override, and then run. ---
**Author:** ![jim](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/jim/32/1976_2.png) [@jim](https://community.openai.com/u/jim)\ **Post date:** [December 15, 2025, 11:25pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/11 "2025-12-15T23:25:34Z")
Jumping on the bandwagon here - `top_p` not supported, but wasn’t in the request - appreciate the .98 hack, but i’ll just wait till its properly fixed… ---
**Author:** ![Vic\_Harding](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/vic_harding/32/634953_2.png) [@Vic\_Harding](https://community.openai.com/u/Vic_Harding)\ **Post date:** [December 15, 2025, 11:48pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/12 "2025-12-15T23:48:19Z")
Ongoing error when I try to begin a session inside any project folder. ---
**Author:** ![matheus.menezes](https://avatars.discourse-cdn.com/v4/letter/m/6a8cbe/32.png) [@matheus.menezes](https://community.openai.com/u/matheus.menezes)\ **Post date:** [December 16, 2025, 5:42pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/13 "2025-12-16T17:42:52Z")
I’m having the same problem: ”HTTP 400 BadRequest: Unsupported parameter: ‘top\_p’ is not supported with this model”. I don’t send top\_p parameter in payload. ---
**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\ **Post date:** [December 16, 2025, 7:22pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/14 "2025-12-16T19:22:39Z")
> [@matheus.menezes](#): > > I don’t send top\_p parameter in payload. Then _do_ send top\_p parameter in the API request payload as described above until OpenAI corrects the model so that any backend `top_p` 1.0 that is meant to be a default is silently cast to the accepted value. The workaround described above. ```auto try: response = client.responses.create( top_p=0.98, # this is required against gpt-5.2 "prompt" settings prompt={ "id": "pmpt_12345", "version": "1" }, input=input_messages, max_output_tokens=12345, store=False, service_tier=None, ) ``` ---
**Author:** ![Tom\_Gagne](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/tom_gagne/32/670516_2.png) [@Tom\_Gagne](https://community.openai.com/u/Tom_Gagne)\ **Post date:** [December 17, 2025, 5:43pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/15 "2025-12-17T17:43:18Z")
The bug for me is when using `"model":"gpt-5.2-pro"`. `gpt-5.2` works fine for me. ---
**Author:** ![Prashant\_Pardesi](https://avatars.discourse-cdn.com/v4/letter/p/f9ae1b/32.png) [@Prashant\_Pardesi](https://community.openai.com/u/Prashant_Pardesi)\ **Post date:** [December 18, 2025, 4:19pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/16 "2025-12-18T16:19:06Z")
Hey everyone, Our engineering team took a look at this issue and have deployed a fix. This issue should now be resolved. Thank you! ---
**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\ **Post date:** [December 18, 2025, 5:02pm UTC](https://community.openai.com/t/gpt-5-2-not-working-with-reusable-prompts-in-responses-api/1369113/17 "2025-12-18T17:02:12Z")
Evaluation of the solution that someone was confident enough to assign to themselves: ## Same “prompt” ID, in conjunction with top\_p: - omitted: success now (`top_p=0.98` echoed) - null value: success now - `1.00`: Unsupported parameter: ‘top\_p’ (same as before) - `0.98`: success (`top_p=0.98` echoed) This means that any existing code you’ve written for reasoning models on Responses, which overrides unsupported parameters with echoed values of top\_p=1 or temperature=1 (as seen on any other model) must be corrected to _drop_ unsupported parameters completely. Except: now not in the case of reasoning.effort:“none” which does take them. Except: but not in “prompts” which still has no facility for altering temperature or top\_p in conjunction with “none” reasoning. Why? Since you cannot anticipate _further_ input default values (that you should be in control of but are not) being messed with as custom model run values picked for you. * * * PS: what the parameters of respecting developers who use your reasoning models and endpoint looks like: ![image](https://us1.discourse-cdn.com/openai1/original/4X/c/0/5/c05b40de8e027449d9d2ed698dbc7323da357546.png)