Describe the bug
When configuring the "Azure OpenAI" node in a Chatflow (e.g. "Legal Case Advisor"), the Model Name field only shows a fixed/predefined list of models (gpt-5.2, gpt-5.2-pro, gpt-5.2-chat-latest, gpt-5.2-codex, gpt-5.1, gpt-5, gpt-5-mini, gpt-5-nano, gpt-4.1, o3-mini, o3, o3-pro, etc.).
Models that correspond to a custom deployment made in Azure (in this case, gpt-5.4-nano) do not appear in the list, even though a Connect Credential is already configured pointing to that deployment (gpt-5.4-nano-suporte-juridico).
To Reproduce
Steps to reproduce the behavior:
Add the Azure OpenAI node to a Chatflow.
Configure a Connect Credential pointing to a custom Azure deployment (e.g. gpt-5.4-nano).
Open the "Model Name" field and type the exact deployment name.
The field only shows autocomplete suggestions from the fixed list of supported models, without including the custom deployment name, even when typing the exact name.
Expected behavior
The "Model Name" field should allow free text entry of the exact deployment name configured in Azure, since in Azure OpenAI the "Model Name" corresponds to the deployment name, which can be any custom string defined by the user — not necessarily a standard OpenAI model name.
Screenshots
(attach the images)
Setup
Provider: Azure OpenAI
Flowise version: (fill in)
Deployment model: gpt-5.4-nano (deployment name: gpt-5.4-nano-suporte-juridico)
Screenshots
Flow
No response
Use Method
Docker
Flowise Version
3.1.2
Operating System
Linux
Browser
Chrome
Additional context
No response
Describe the bug
When configuring the "Azure OpenAI" node in a Chatflow (e.g. "Legal Case Advisor"), the Model Name field only shows a fixed/predefined list of models (gpt-5.2, gpt-5.2-pro, gpt-5.2-chat-latest, gpt-5.2-codex, gpt-5.1, gpt-5, gpt-5-mini, gpt-5-nano, gpt-4.1, o3-mini, o3, o3-pro, etc.).
Models that correspond to a custom deployment made in Azure (in this case, gpt-5.4-nano) do not appear in the list, even though a Connect Credential is already configured pointing to that deployment (gpt-5.4-nano-suporte-juridico).
To Reproduce
Steps to reproduce the behavior:
Add the Azure OpenAI node to a Chatflow.
Configure a Connect Credential pointing to a custom Azure deployment (e.g. gpt-5.4-nano).
Open the "Model Name" field and type the exact deployment name.
The field only shows autocomplete suggestions from the fixed list of supported models, without including the custom deployment name, even when typing the exact name.
Expected behavior
The "Model Name" field should allow free text entry of the exact deployment name configured in Azure, since in Azure OpenAI the "Model Name" corresponds to the deployment name, which can be any custom string defined by the user — not necessarily a standard OpenAI model name.
Screenshots
(attach the images)
Setup
Provider: Azure OpenAI
Flowise version: (fill in)
Deployment model: gpt-5.4-nano (deployment name: gpt-5.4-nano-suporte-juridico)
Screenshots
Flow
No response
Use Method
Docker
Flowise Version
3.1.2
Operating System
Linux
Browser
Chrome
Additional context
No response