GPT-5.4 Mini

GPT-5.4 Mini is a OpenAI model available in Agent Serve. GPT-5.4 Mini is a OpenAI model tracked in Agent Serve. It supports a 400k token context window. Pricing starts at $0.75/1M input tokens and $4.5/1M output tokens. Key capabilities include Tool choice, Structured outputs, Reasoning none, low, medium, high, xhigh.

GPT-5.4 Mini starts at $0.75/1M input tokens, $0.075/1M cached input tokens, and $4.5/1M output tokens.

GPT-5.4 Mini supports a context window of 400k 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 Mini supports the following capabilities in Agent Serve: Tool choice, Structured outputs, Reasoning none, low, medium, high, xhigh, 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.