About
GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...
Related Models
Pricing
Input
$2.00
per 1M tokens
Output
$8.00
per 1M tokens
Blended
$3.50
per 1M tokens
Cheaper than 15% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$3.50
Monthly
$105.00
vs. Similar Models
MoonshotAI: Kimi K2 0711Q:0.0
$1.00-71%
inclusionAI: Ling-2.6-flashQ:-0.1
$0.01-100%
GLM-4.5 (Reasoning)Q:+0.1
$1.00-71%
Qwen3 Max (Preview)Q:-0.2
$2.40-31%
Performance
122
tokens/sec
Faster than 65% of models
0.57
seconds
Faster than 80% of models
0.57
seconds
Faster than 86% of models
Market Median
94 tok/s
30% faster
Median TTFT
1.10s
48% faster
Throughput/Dollar
35
tok/s per $/1M
Speed Comparison
GPT-4o (Aug '24)
121 tok/s-0%
Qwen: Qwen3 VL 30B A3B Instruct
121 tok/s-1%
Nex AGI: Nex-N2-Pro
121 tok/s-1%
Context Window
1.0M
tokens
Larger than 89% of models
Max Output
33K
tokens
3% of context
Benchmarks
MMLU-Pro
80.6%
GPQA Diamond
66.6%
HLE
4.6%
LiveCodeBench
45.7%
SciCode
38.1%
TerminalBench Hard
13.6%
MATH-500
91.3%
AIME
43.7%
AIME 2025
34.7%
IFBench
43.0%
Long Context Recall
61.0%
Tau2
47.1%
Market AverageTop Score