OpenAI GPT-5.4 mini - Box Dev Docs

According to OpenAI, OpenAI GPT-5.4 mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads.

Model details

Item	Value	Description
Model name	GPT-5.4 mini	The name of the model.
Model category	Standard	The category of the model: Standard or Premium.
API model name	`openai__gpt_5_4_mini`	The name of the model that is used in the . You must provide this exact name for the API to work.
Compliance	N/A	Government compliance frameworks and authorizations applicable to this model.
Hosting layer	OpenAI	The trusted organization that securely hosts the LLM.
Model provider	OpenAI	The organization that provides this model.
Release date	March 17th, 2026	The release date for the model.
Knowledge cutoff date	August 31st, 2025	The date after which the model does not get any information updates.
Input context window	400k tokens	The number of tokens supported by the input context window.
Maximum output tokens	128k tokens	The number of tokens that can be generated by the model in a single request.
Empirical throughput	Not specified	The number of tokens the model can generate per second.
Open source	No	Specifies if the model’s code is available for public use.

Additional documentation

For additional information, see official OpenAI GPT-5.4 mini documentation.

Last modified on June 2, 2026

⌘I