> ## Documentation Index
> Fetch the complete documentation index at: https://developer.watson-orchestrate.ibm.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Using GPT-5.4

GPT-5.4 is one of OpenAI's frontier models, available in watsonx Orchestrate through Azure. This page covers model-specific behavior and agent configuration that are relevant to developers and agent builders who use GPT-5.4.

<Note>
  GPT-5.4 is a premier model and must be enabled by a tenant administrator before it can be used. See [Enabling premier models](enable_premier_models) for instructions.
</Note>

## Agent styles

GPT-5.4 always uses the **ReAct Core (`react_core`)** agent style, regardless of the style that is set on your agent. You do not need to configure this explicitly as it is applied automatically.

Agent behavior with GPT-5.4 is architecturally similar to GPT-OSS-120B: the same instruction patterns, tool usage rules, and prompt engineering practices apply. If you have agents that are already tuned for GPT-OSS-120B, they are a solid starting point.

Model behavior is not identical across versions. When you switch to GPT-5.4, you might find that some instructions must be tightened, softened, or reworded to get the same results.

## Tool name constraints

GPT-5.4 is served through Azure and enforces the [OpenAI function object specification](https://learn.microsoft.com/en-us/rest/api/microsoft-foundry/azureopenai/chat?view=rest-microsoft-foundry-v1\&preserve-view=true#openaifunctionobject). One constraint that may require changes when you move from GPT-OSS-120B on Groq is the **tool name format**.

watsonx Orchestrate uses the **display name** of a tool when it builds the function payload that is sent to the model. The display name must therefore conform to the Azure specification:

> Display names must match `^[a-zA-Z0-9_-]{1,64}$` — only letters, numbers, underscores, and hyphens, with a maximum length of 64 characters.

This applies to the display names of all tool types that are registered with the agent:

* **Skills and tools**: The skill display name that is sent in the LLM payload.
* **Knowledge bases**: The display name that is used to identify the retrieval tool.
* **Collaborator agents**: The display name that the model uses to invoke a subagent.

## Prompt guide

GPT-5.4 uses the same **ReAct Core (`react_core`)** agent style as GPT-OSS-120B, so the same prompt engineering principles apply. For instruction templates, tool usage rules, and best practices, see the [GPT-OSS-120B prompt guide](./migrating_to_gpt_oss#optimize-agent-instructions).