Loading...
Loading...
For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...
Input
$0.10
per 1M tokens
Output
$0.40
per 1M tokens
Blended
$0.17
per 1M tokens
Cheaper than 73% of models. Median price is $0.56/1M tokens.
Daily
$0.17
Monthly
$5.25
113
tokens/sec
Faster than 63% of models
0.55
seconds
Faster than 78% of models
0.55
seconds
Faster than 86% of models
Market Median
86 tok/s
32% faster
Median TTFT
1.07s
49% faster
Throughput/Dollar
647
tok/s per $/1M
Speed Comparison
Context Window
1.0M
tokens
Larger than 90% of models
Max Output
33K
tokens
3% of context
Quality Index
13.0
368th of 507
Top 73%
Coding Index
11.2
302nd of 417
Top 73%
Math Index
24.0
200th of 269
Top 75%
Price/1M
$0.17
161st cheapest
69% below median
Top 27%
Speed
113 tok/s
Top 37%
TTFT
0.55s
Context Window
1.0M
38th largest
Top 10%