gpt-5.1-codex-max support in plugin:Azure OpenAI Service Model #915

Closed
opened 2026-02-16 10:20:56 -05:00 by yindo · 5 comments
Owner

Originally created by @cwk0099 on GitHub (Jan 4, 2026).

Self Checks

  • I have read the Contributing Guide and Language Policy.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report, otherwise it will be closed.
  • Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

I added the model gpt-5.1-codex-max in this plugin, and it showed me the following error.gpt-5.1 works, but codex doesn’t.I hope the codex model can be supported.

Error code: 400 - {'error': {'code': 'OperationNotSupported', 'message': 'The chatCompletion operation does not work with the specified model, gpt-5.1-codex-max. Please choose different model and try again. You can learn more about which models can be used with each operation here: https://go.microsoft.com/fwlink/?linkid=2197993.'}}

2. Additional context or comments

dify:1.10.1
plugin:Azure OpenAI Service Model
plugin version :0.0.34

3. Can you help us with this feature?

  • I am interested in contributing to this feature.
Originally created by @cwk0099 on GitHub (Jan 4, 2026). ### Self Checks - [x] I have read the [Contributing Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) and [Language Policy](https://github.com/langgenius/dify/issues/1542). - [x] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify-official-plugins/issues), including closed ones. - [x] I confirm that I am using English to submit this report, otherwise it will be closed. - [x] Please do not modify this template :) and fill in all the required fields. ### 1. Is this request related to a challenge you're experiencing? Tell me about your story. I added the model gpt-5.1-codex-max in this plugin, and it showed me the following error.gpt-5.1 works, but codex doesn’t.I hope the codex model can be supported. Error code: 400 - {'error': {'code': 'OperationNotSupported', 'message': 'The chatCompletion operation does not work with the specified model, gpt-5.1-codex-max. Please choose different model and try again. You can learn more about which models can be used with each operation here: https://go.microsoft.com/fwlink/?linkid=2197993.'}} ### 2. Additional context or comments dify:1.10.1 plugin:Azure OpenAI Service Model plugin version :0.0.34 ### 3. Can you help us with this feature? - [ ] I am interested in contributing to this feature.
yindo added the bugenhancement labels 2026-02-16 10:20:56 -05:00
yindo closed this issue 2026-02-16 10:20:56 -05:00
Author
Owner

@dosubot[bot] commented on GitHub (Jan 4, 2026):

Support for gpt-5.1-codex-max in the Azure OpenAI Service Model plugin has recently improved. As of plugin version 0.0.34, models whose names start with gpt-5.1-codex (including gpt-5.1-codex-max) are routed to the Responses API for chat generation, which should resolve the OperationNotSupported error you saw with chatCompletion operations. This change is included in your current plugin version, so you should be able to use gpt-5.1-codex-max if your Azure deployment is in a supported region and you have access to the model (details).

If you still encounter errors, double-check that your deployment is using plugin version 0.0.34, your Azure region is East US2 or Sweden Central, and your model registration is complete (reference). Also, ensure that required parameters like max_output_tokens are set appropriately, as the Responses API expects them.

If issues persist, check the plugin logs for details and confirm that your configuration matches the latest plugin requirements.

To reply, just mention @dosu.


How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other

Open in Cursor Join Discord Share on X

@dosubot[bot] commented on GitHub (Jan 4, 2026): <!-- Answer --> Support for gpt-5.1-codex-max in the Azure OpenAI Service Model plugin has recently improved. As of plugin version 0.0.34, models whose names start with gpt-5.1-codex (including gpt-5.1-codex-max) are routed to the Responses API for chat generation, which should resolve the OperationNotSupported error you saw with chatCompletion operations. This change is included in your current plugin version, so you should be able to use gpt-5.1-codex-max if your Azure deployment is in a supported region and you have access to the model ([details](https://github.com/langgenius/dify-official-plugins/pull/2265)). If you still encounter errors, double-check that your deployment is using plugin version 0.0.34, your Azure region is East US2 or Sweden Central, and your model registration is complete ([reference](https://github.com/langgenius/dify-official-plugins/issues/2192)). Also, ensure that required parameters like max_output_tokens are set appropriately, as the Responses API expects them. If issues persist, check the plugin logs for details and confirm that your configuration matches the latest plugin requirements. <!-- Dosu Comment Footer --> *To reply, just mention [@dosu](https://go.dosu.dev/dosubot).* --- <sup>How did I do? [Good](https://app.dosu.dev/response-feedback/31f612a5-b50a-42c7-ba0a-a6ffd6071b47?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/31f612a5-b50a-42c7-ba0a-a6ffd6071b47?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/31f612a5-b50a-42c7-ba0a-a6ffd6071b47?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/31f612a5-b50a-42c7-ba0a-a6ffd6071b47?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/31f612a5-b50a-42c7-ba0a-a6ffd6071b47?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/31f612a5-b50a-42c7-ba0a-a6ffd6071b47?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/31f612a5-b50a-42c7-ba0a-a6ffd6071b47?feedback_type=other)</sup> [![Open in Cursor](https://dosu.dev/dosu-in-cursor.svg)](https://cursor.com/link/prompt?text=Support%20for%20gpt-5.1-codex-max%20in%20the%20Azure%20OpenAI%20Service%20Model%20plugin%20has%20recently%20improved.%20As%20of%20plugin%20version%200.0.34%2C%20models%20whose%20names%20start%20with%20gpt-5.1-codex%20%28including%20gpt-5.1-codex-max%29%20are%20routed%20to%20the%20Responses%20API%20for%20chat%20generation%2C%20which%20should%20resolve%20the%20OperationNotSupported%20error%20you%20saw%20with%20chatCompletion%20operations.%20This%20change%20is%20included%20in%20your%20current%20plugin%20version%2C%20so%20you%20should%20be%20able%20to%20use%20gpt-5.1-codex-max%20if%20your%20Azure%20deployment%20is%20in%20a%20supported%20region%20and%20you%20have%20access%20to%20the%20model%C2%A0%28%5Bdetails%5D%28https%3A//github.com/langgenius/dify-official-plugins/pull/2265%29%29.%0A%0AIf%20you%20still%20encounter%20errors%2C%20double-check%20that%20your%20deployment%20is%20using%20plugin%20version%200.0.34%2C%20your%20Azure%20region%20is%20East%20US2%20or%20Sweden%20Central%2C%20and%20your%20model%20registration%20is%20complete%C2%A0%28%5Breference%5D%28https%3A//github.com/langgenius/dify-official-plugins/issues/2192%29%29.%20Also%2C%20ensure%20that%20required%20parameters%20like%20max_output_tokens%20are%20set%20appropriately%2C%20as%20the%20Responses%20API%20expects%20them.%0A%0AIf%20issues%20persist%2C%20check%20the%20plugin%20logs%20for%20details%20and%20confirm%20that%20your%20configuration%20matches%20the%20latest%20plugin%20requirements.)&nbsp;[![Join Discord](https://img.shields.io/badge/join-5865F2?logo=discord&logoColor=white&label=)](https://go.dosu.dev/discord-bot)&nbsp;[![Share on X](https://img.shields.io/badge/X-share-black)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify-official-plugins/issues/2359)
Author
Owner

@cwk0099 commented on GitHub (Jan 4, 2026):

Image Image Image I have already checked the configuration and everything seems fine. My API endpoint is set to:https://xxxxeastus2.cognitiveservices.azure.com/ Could you confirm if this endpoint is incorrect? Also, gpt-5.1 works fine, but the codex model does not. I hope support for the codex model can be added. @dosu
@cwk0099 commented on GitHub (Jan 4, 2026): <img width="1160" height="502" alt="Image" src="https://github.com/user-attachments/assets/af39b723-0220-45bc-8ecd-0d6b590fdd86" /> <img width="425" height="368" alt="Image" src="https://github.com/user-attachments/assets/942128a2-894f-4b44-b8dc-cfced6876cb4" /> <img width="1065" height="848" alt="Image" src="https://github.com/user-attachments/assets/9ccf18d4-210b-4303-a99c-f61a45c3f614" /> I have already checked the configuration and everything seems fine. My API endpoint is set to:https://xxxxeastus2.cognitiveservices.azure.com/ Could you confirm if this endpoint is incorrect? Also, gpt-5.1 works fine, but the codex model does not. I hope support for the codex model can be added. @dosu
Author
Owner

@dosubot[bot] commented on GitHub (Jan 4, 2026):

Your endpoint format and region (East US2) are correct for gpt-5.1-codex-max. The plugin version 0.0.34 is intended to support this model by routing it to the Responses API instead of the chatCompletion API, which should avoid the OperationNotSupported error you’re seeing (details).

If you still get this error, double-check that your Azure deployment and model registration are complete and that the deployment/model names in Azure exactly match what you’ve configured in Dify. Also, make sure the plugin is actually calling the Responses API (not chatCompletion) by reviewing plugin logs. If the plugin is routing correctly and you still see errors, check your Azure portal for registration or quota issues.

If you need a workaround, you can use the Responses API directly—there’s a sample code gist showing how to do this with gpt-5.1-codex-max (reference). If the problem persists, sharing plugin logs or error details will help diagnose any remaining issues.

To reply, just mention @dosu.


How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other

Open in Cursor Join Discord Share on X

@dosubot[bot] commented on GitHub (Jan 4, 2026): <!-- Answer --> Your endpoint format and region (East US2) are correct for gpt-5.1-codex-max. The plugin version 0.0.34 is intended to support this model by routing it to the Responses API instead of the chatCompletion API, which should avoid the OperationNotSupported error you’re seeing ([details](https://github.com/langgenius/dify-official-plugins/pull/2265)). If you still get this error, double-check that your Azure deployment and model registration are complete and that the deployment/model names in Azure exactly match what you’ve configured in Dify. Also, make sure the plugin is actually calling the Responses API (not chatCompletion) by reviewing plugin logs. If the plugin is routing correctly and you still see errors, check your Azure portal for registration or quota issues. If you need a workaround, you can use the Responses API directly—there’s a sample code gist showing how to do this with gpt-5.1-codex-max ([reference](https://github.com/langgenius/dify-official-plugins/issues/2216#issuecomment-3632192758)). If the problem persists, sharing plugin logs or error details will help diagnose any remaining issues. <!-- Dosu Comment Footer --> *To reply, just mention [@dosu](https://go.dosu.dev/dosubot).* --- <sup>How did I do? [Good](https://app.dosu.dev/response-feedback/891c661f-b5bc-4afd-acdf-d91812975d2d?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/891c661f-b5bc-4afd-acdf-d91812975d2d?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/891c661f-b5bc-4afd-acdf-d91812975d2d?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/891c661f-b5bc-4afd-acdf-d91812975d2d?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/891c661f-b5bc-4afd-acdf-d91812975d2d?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/891c661f-b5bc-4afd-acdf-d91812975d2d?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/891c661f-b5bc-4afd-acdf-d91812975d2d?feedback_type=other)</sup> [![Open in Cursor](https://dosu.dev/dosu-in-cursor.svg)](https://cursor.com/link/prompt?text=Your%20endpoint%20format%20and%20region%20%28East%20US2%29%20are%20correct%20for%20gpt-5.1-codex-max.%20The%20plugin%20version%200.0.34%20is%20intended%20to%20support%20this%20model%20by%20routing%20it%20to%20the%20Responses%20API%20instead%20of%20the%20chatCompletion%20API%2C%20which%20should%20avoid%20the%20OperationNotSupported%20error%20you%E2%80%99re%20seeing%C2%A0%28%5Bdetails%5D%28https%3A//github.com/langgenius/dify-official-plugins/pull/2265%29%29.%0A%0AIf%20you%20still%20get%20this%20error%2C%20double-check%20that%20your%20Azure%20deployment%20and%20model%20registration%20are%20complete%20and%20that%20the%20deployment/model%20names%20in%20Azure%20exactly%20match%20what%20you%E2%80%99ve%20configured%20in%20Dify.%20Also%2C%20make%20sure%20the%20plugin%20is%20actually%20calling%20the%20Responses%20API%20%28not%20chatCompletion%29%20by%20reviewing%20plugin%20logs.%20If%20the%20plugin%20is%20routing%20correctly%20and%20you%20still%20see%20errors%2C%20check%20your%20Azure%20portal%20for%20registration%20or%20quota%20issues.%0A%0AIf%20you%20need%20a%20workaround%2C%20you%20can%20use%20the%20Responses%20API%20directly%E2%80%94there%E2%80%99s%20a%20sample%20code%20gist%20showing%20how%20to%20do%20this%20with%20gpt-5.1-codex-max%C2%A0%28%5Breference%5D%28https%3A//github.com/langgenius/dify-official-plugins/issues/2216%23issuecomment-3632192758%29%29.%20If%20the%20problem%20persists%2C%20sharing%20plugin%20logs%20or%20error%20details%20will%20help%20diagnose%20any%20remaining%20issues.)&nbsp;[![Join Discord](https://img.shields.io/badge/join-5865F2?logo=discord&logoColor=white&label=)](https://go.dosu.dev/discord-bot)&nbsp;[![Share on X](https://img.shields.io/badge/X-share-black)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify-official-plugins/issues/2359)
Author
Owner

@cwk0099 commented on GitHub (Jan 4, 2026):

there is no model name:gpt-5.1-codex-max in LLM_BASE_MODELS

Image so get false here. It seems that gpt-5.1-codex-max is not supported.@dosu Image
@cwk0099 commented on GitHub (Jan 4, 2026): there is no model name:gpt-5.1-codex-max in LLM_BASE_MODELS <img width="1248" height="724" alt="Image" src="https://github.com/user-attachments/assets/ab951c51-adaa-4819-93bc-d4929bd3b566" /> so get false here. It seems that gpt-5.1-codex-max is not supported.@dosu <img width="1202" height="593" alt="Image" src="https://github.com/user-attachments/assets/5eb097d0-93c7-439f-86f4-86379a7af97a" />
Author
Owner

@cwk0099 commented on GitHub (Jan 4, 2026):

Image The validate_credentials method has not yet been updated, which causes gpt-5.1-codex to be ineffective and also use chat mode.
@cwk0099 commented on GitHub (Jan 4, 2026): <img width="1394" height="749" alt="Image" src="https://github.com/user-attachments/assets/b8292c23-f49e-4be0-b3be-4df4cf10a872" /> The validate_credentials method has not yet been updated, which causes gpt-5.1-codex to be ineffective and also use chat mode.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify-official-plugins#915