Error 400 response_format value as json_schema is not supported

[nabdoul]

What happened?

Hello,

I’ve just set up image generation using Azure OpenAI deployments.

Image generation works fine, but at the end of the process, I get the following error message:

LibreChat | 2025-07-09 10:24:58 error: [api/server/controllers/agents/client.js #titleConvo] Error 400 Invalid parameter: 'response_format' of type 'json_schema' is not supported with this model. Learn more about supported models at the Structured Outputs guide: https://platform.openai.com/docs/guides/structured-outputs

Here is the configuration file:

endpoints:
azureOpenAI:
titleModel: "GPT-4o"
titleConvo: true
titleMethod: "functions"
groups:
- group: "gpt-4o"
apiKey: "xx"
instanceName: "xx"
version: "2025-01-01-preview"
baseURL: "xx"
models:
GPT-4o:
deploymentName: "xxx"

Could you please help me resolve this issue?

Thank you in advance for your support.
Best regards,

Version Information

ghcr.io/danny-avila/librechat-dev latest 2ede259a0a67
ghcr.io/danny-avila/librechat latest 92d57359fc25
ghcr.io/danny-avila/librechat-rag-api-dev-lite latest 6550e7ddf180

Steps to Reproduce

Image generation works fine, but at the end of the process, I get the following error message

What browsers are you seeing the problem on?

No response

Relevant log output

| 2025-07-09 10:24:58 error: [api/server/controllers/agents/client.js #titleConvo] Error 400 Invalid parameter: 'response_format' of type 'json_schema' is not supported with this model. Learn more about supported models at the Structured Outputs guide: https://platform.openai.com/docs/guides/structured-outputs

Screenshots

No response

Code of Conduct

• I agree to follow this project's Code of Conduct

[danny-avila]

this is expected, and a non-structured output method for titling will soon be added.