GPT-5.4

GPT-5.4 is a Azure OpenAI model available in Agent Serve. GPT-5.4 is a Azure OpenAI model tracked in Agent Serve. It supports a 1.05M token context window. Pricing starts at $2.5/1M input tokens and $15/1M output tokens. Key capabilities include Tool choice, Structured outputs, Reasoning low, medium, high.

GPT-5.4 starts at $2.5/1M input tokens, $0.25/1M cached input tokens, and $15/1M output tokens.

GPT-5.4 supports a context window of 1.05M tokens in Agent Serve. In an agent, this determines how much conversation history, tool outputs, and retrieved documents the model can hold in a single call.

GPT-5.4 supports the following capabilities in Agent Serve: Tool choice, Structured outputs, Reasoning low, medium, high, Verbosity low, medium, high, Max output 128k.

Best for reasoning-heavy tasks that need more deliberate model control. When used in an Agent Serve workflow, it can be selected in any Agent block from the model picker.