Loading...
Loading...
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 GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.
Quality Index
26.3
130th of 444
Top 30%
Coding Index
21.8
137th of 354
Top 39%
Math Index
34.7
174th of 268
Top 65%
Price/1M
$3.50
594th cheapest
1067% above median
Top 88%
Speed
85 tok/s
Top 30%
TTFT
0.52s
Context Window
1.0M
23rd largest
Top 7%
Input
$2.00
per 1M tokens
Output
$8.00
per 1M tokens
Blended
$3.50
per 1M tokens
Cheaper than 12% of models. Median price is $0.30/1M tokens.
Daily
$3.50
Monthly
$105.00
85
tokens/sec
Faster than 70% of models
0.52
seconds
Faster than 44% of models
0.52
seconds
Faster than 47% of models
Market Median
45 tok/s
88% faster
Median TTFT
0.42s
24% slower
Throughput/Dollar
24
tok/s per $/1M
Speed Comparison
Context Window
1.0M
tokens
Larger than 93% of models
Max Output
33K
tokens
3% of context