MARKETS OPEN
GPT-4o$2.513 1.59%
AWS-C7G$0.0577 1.08%
CLAUDE-3.5S$3.015 0.01%
GPT-4o-mini$0.1488 2.18%
GEM-2F$0.0568 0.66%
GCP-C3$0.0629 9.11%
GEM-1.5P$1.226 3.60%
AWS-P5$121.47 4.38%
o1$15.103 2.21%
CLAUDE-3.5H$0.7923 0.08%
AZ-DV5$0.1137 0.47%
DS-R1$0.6930 3.55%
LLAMA-3.3$0.1960 0.48%
o1-mini$3.029 0.57%
GPT-4o$2.513 1.59%
AWS-C7G$0.0577 1.08%
CLAUDE-3.5S$3.015 0.01%
GPT-4o-mini$0.1488 2.18%
GEM-2F$0.0568 0.66%
GCP-C3$0.0629 9.11%
GEM-1.5P$1.226 3.60%
AWS-P5$121.47 4.38%
o1$15.103 2.21%
CLAUDE-3.5H$0.7923 0.08%
AZ-DV5$0.1137 0.47%
DS-R1$0.6930 3.55%
LLAMA-3.3$0.1960 0.48%
o1-mini$3.029 0.57%
Back to markets
OpenAI · Fast

GPT-4o-mini

GPT-4o mini

$0.1488
2.18% · 24h
$0.1267 13.88%30D
View
MA
Forecast
Range
24h change
-2.18% 2.18%
7d change
-2.27% 2.27%
Context window
128k
tokens
API status
LIVE
Updated 7:30:01 PM

Price breakdown

Input tokens$0.1500 / 1M tok
Output tokens$0.6000 / 1M tok
Cached input$0.0750 / 1M tok

How OpenAI bills

Method
Per million tokens (input/output)
Explanation
OpenAI bills separately for input tokens (what you send) and output tokens (what the model generates). Caching reduces input cost on repeated prompts.