GPT-5.4 Mini

reasoningproprietary

GPT-5.4 Mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads. Learn more in our Model guidance page. Reasoning.effort supports: none (default), low, medium, high and xhigh.

Intelligence
Reasoning
Speed
Context
400K
Max output
128K
Input price
$0.75/1M tokens
Output price
$4.5/1M tokens
Snapshotsgpt-5.4-mini-2026-03-17

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Batch Processing

Details

Model IDgpt-5.4-mini
Provider OpenAI
Creator openai
Familygpt-5.4
Licenseproprietary
Statusactive
Typereasoning
Input modalitiestext, image
Output modalitiestext
Open weightNo
Parameters—
Architecture—
Context window400K tokens
Max input272K tokens
Max output128K tokens
Reasoning tokensYes
Knowledge cutoff
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs
Web Searchweb_search
Search the web for information
File Searchfile_search
Search across uploaded files
Tool Searchtool_search
Discover and use tools
Image Generationimage_generation
Generate images inline
Code Interpretercode_interpreter
Execute code in a sandbox
Hosted Shellhosted_shell
Run shell commands in a container
Apply Patchapply_patch
Apply code patches to files
Skillsskills
Use built-in skill modules
Computer Usecomputer_use
Control a virtual desktop
MCPmcp
Connect to Model Context Protocol servers

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.openai.com/v1/chat/completions
ResponsesPOST
Stateful multi-turn conversationshttps://api.openai.com/v1/responses
BatchPOST
Async batch processing at lower costhttps://api.openai.com/v1/batches

Pricing

Text tokensPer 1M tokens
InputCached inputOutput
Standard$0.75$0.075$4.5

Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.4 Mini.

Family Comparison: gpt-5.4

ModelContextMax outPricing
GPT-5.4 nano400K128K$0.2$1.25
GPT-5.4 Mini400K128K$0.75$4.5
GPT-5.41.1M128K$2.5$15
GPT-5.4 Pro1.1M128K$30$180

API

GET/v1/models/openai/gpt-5.4-mini

GPT-5.4 Mini

gpt-5.4-mini

GPT-5.4 Mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads. Learn more in our Model guidance page. Reasoning.effort supports: none (default), low, medium, high and xhigh.

gpt-5.4-mini-2026-03-17
Changes · 11 entries
gpt-5.4-miniupdateca7a400Nov 2, 2026, 03:02 AM
nameGPT-5.4 mini→GPT-5.4 Mini
descriptionGPT-5.4 mini brings the strengths of GPT-5.4 to a faster,...→GPT-5.4 Mini brings the strengths of GPT-5.4 to a faster,...
model_typechat→reasoning
pricingtiers[{"label":"Text tokens","unit":"Per 1M tokens","columns":...→[{"label":"Text tokens","unit":"Per 1M tokens","columns":...
tools["function_calling"]→["function_calling","web_search","file_search","tool_sear...
endpoints["responses","chat_completions","batch"]→["chat_completions","responses","batch"]
pricing_notes["Regional processing (data residency) endpoints are char...→["Regional processing (data residency) endpoints are char...
page_urlhttps://developers.openai.com/api/docs/models/gpt-5.4-min...→https://developers.openai.com/api/docs/models/gpt-5.4-mini
gpt-5.4-miniupdate4e8b6afOct 21, 2026, 06:35 AM
pricingtiers[{"label":"Text tokens","unit":"Per 1M tokens","columns":...→[{"label":"Text tokens","unit":"Per 1M tokens","columns":...
gpt-5.4-miniupdate118451aSep 24, 2026, 07:08 AM
descriptionGPT-5.4 Mini brings the strengths of GPT-5.4 to a faster,...→GPT-5.4 Mini brings the strengths of GPT-5.4 to a faster,...
pricingtiers[{"label":"Text tokens","unit":"Per 1M tokens","columns":...→[{"label":"Text tokens","unit":"Per 1M tokens","columns":...
endpoints["responses","chat_completions","batch"]→["chat_completions","responses","batch"]
gpt-5.4-miniupdatee3d7dedAug 31, 2026, 04:13 AM
nameGPT-5.4 mini→GPT-5.4 Mini
descriptionGPT-5.4 mini brings the strengths of GPT-5.4 to a faster,...→GPT-5.4 Mini brings the strengths of GPT-5.4 to a faster,...
model_typechat→reasoning
tools["function_calling"]→["function_calling","web_search","file_search","tool_sear...
pricing_notes["Regional processing (data residency) endpoints are char...→["Regional processing (data residency) endpoints are char...
page_urlhttps://developers.openai.com/api/docs/models/gpt-5.4-min...→https://developers.openai.com/api/docs/models/gpt-5.4-mini
gpt-5.4-miniupdate6ee7faeMar 26, 2026, 06:57 PM
pricingtiers[{"label":"Text tokens","unit":"Per 1M tokens","columns":...→[{"label":"Text tokens","unit":"Per 1M tokens","columns":...
gpt-5.4-miniupdatefa2bbbbMar 24, 2026, 05:22 AM
capabilitiesjson modeno→yes
gpt-5.4-miniupdatef43e286Mar 24, 2026, 04:45 AM
capabilitiesjson modeyes→nofine tuningnobatchyes
gpt-5.4-miniupdate1cd659eMar 24, 2026, 04:19 AM
capabilitiesjson modeyes
page_urlhttps://platform.openai.com/docs/models/gpt-5.4-mini→https://developers.openai.com/api/docs/models/gpt-5.4-min...
gpt-5.4-miniupdate2b100acMar 23, 2026, 05:30 AM
model_typereasoning→chat
tools["function_calling","web_search","file_search","tool_sear...→["function_calling"]
licenseproprietary
page_urlhttps://platform.openai.com/docs/models/gpt-5.4-mini
open_weightno
release_date2026-03-17
gpt-5.4-miniupdateb50649fMar 21, 2026, 11:58 PM
namegpt-5.4-mini→GPT-5.4 mini
pricingtiers[{"label":"Text tokens","unit":"Per 1M tokens","columns":...
knowledge_cutoff2025-08
max_input_tokens272000
reasoning_tokensyes
reasoning4
taglineOur strongest mini model yet for coding, computer use, an...
tools["function_calling","web_search","file_search","tool_sear...
endpoints["responses","chat_completions","batch"]
pricing_notes["Regional processing (data residency) endpoints are char...
gpt-5.4-minicreate7f5c66fMar 21, 2026, 05:16 AM