OpenAI

GPT-5.4 Mini

by OpenAItext+image+file->text5 endpoints
Neura Intelligence Index
46.7/ 100
Rank
#191
Confidence
medium
Benchmarks
7(18% coverage)

Overview

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...

Capabilities

Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Deterministic seed

Modalities

Input
FileImageText
Output
Text

Technical Specifications

Context Window
400K tokens
Max Output
128K tokens
Knowledge Cutoff
2025-08-31
Tokenizer
GPT
Content Moderation
Enabled
Uptime (24h)
10000.0%
Country
🇺🇸US
Release Date
March 17, 20266mo

Supported Parameters

include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetools

Benchmark Performance

general

BenchmarkScoreSource
MRCR v2
33.6
verified

coding

BenchmarkScoreSource
SWE-Bench Pro
54.4
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
88
verified
Humanity's Last Exam
28.2
verified

multimodal

BenchmarkScoreSource
MMMU-Pro
76.6
verified

agent

BenchmarkScoreSource
MCP Atlas
57.7
verified
Toolathlon
42.9
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.75
Output$4.50
Cache read$0.07
Added
March 17, 2026
Last synced 9/16/2026