o4-mini-2025-04-16 vs o3-2025-04-16
Pricing, Performance & Features Comparison
Our faster, cost-efficient reasoning model delivering strong performance on math, coding and vision
Input$1.1
Output$4.4
Latency (p50)2.5s
Output Limit100K
Function Calling
JSON Mode
InputText, Image
OutputText
in$1.1out$4.4cache$0.28–
Latency (24h)
Success Rate (24h)
Our most powerful reasoning model with leading performance on coding, math, science, and vision
Input$2
Output$8
Latency (p50)2.5s
Output Limit100K
Function Calling
JSON Mode
InputText, Image
OutputText
in$2out$8cache$0.5–