GPT-5.4 mini

GPT-5.4 mini is a small model from OpenAI for coding subagents, quick tool use, and high-volume work. It is part of the gpt-mini line, released on 2026-03-17. It has a 400,000 token context window and a 128,000 token maximum output. It accepts image and text inputs and returns text. It supports reasoning mode and tool calling. The weights are not open. Pricing starts at $0.375 per million input tokens and $3.60 per million output tokens, with cached input at $0.0375 per million tokens.

Against GPT-5 Mini: input $0.04 to $0.375, output $0.29 to $3.60, cached input $0.022 to $0.0375.

Range across the hosts that serve it: up to $1.50 per 1M input tokens.

• ·400k token context window for long tasks
• ·128k token maximum output
• ·Supports reasoning mode
• ·Supports tool calling
• ·Accepts image and text inputs

• Reach for it for coding subagents
• Reach for it for quick tool use
• Reach for it for high-volume work

32 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window and maximum output?

Context window is 400,000 tokens, maximum output is 128,000 tokens.

Does it support tool calling and reasoning?

Yes, it supports both reasoning mode and tool calling.

What is the pricing?

Input from $0.375 per million tokens, output $3.60 per million, cached input $0.0375 per million.