About
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,...
Related Models
Pricing
Input
$0.75
per 1M tokens
Output
$4.50
per 1M tokens
Blended
$1.69
per 1M tokens
Cheaper than 27% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$1.69
Monthly
$50.63
vs. Similar Models
Qwen3.6 Max PreviewQ:0.0
$2.92+73%
MiMo-V2.5Q:+0.1
$0.17-90%
OpenAI: GPT-5.2-CodexQ:+0.1
$4.81+185%
Z.ai: GLM 5.1Q:+0.2
$1.50-11%
Performance
182
tokens/sec
Faster than 82% of models
6.35
seconds
Faster than 15% of models
6.35
seconds
Faster than 45% of models
Market Median
94 tok/s
93% faster
Median TTFT
1.11s
470% slower
Throughput/Dollar
108
tok/s per $/1M
Speed Comparison
OpenAI: GPT-4.1 Nano
182 tok/s+0%
OpenAI: o4 Mini
183 tok/s+0%
Nemotron 3 Ultra 550B A55B (Reasoning)
183 tok/s+1%
Context Window
400K
tokens
Larger than 76% of models
Max Output
128K
tokens
32% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
87.5%
HLE
26.6%
LiveCodeBenchNot evaluated
SciCode
49.9%
TerminalBench Hard
52.3%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
73.3%
Long Context Recall
69.3%
Tau2
83.3%
Market AverageTop Score