gpt-4.1-nano-2025-04-14 vs gpt-4.1-2025-04-14
Pricing, Performance & Features Comparison
GPT-4.1 nano is the fastest, most cost-effective GPT 4.1 model.
Input$0.1
Output$0.4
Latency (p50)771ms
Output Limit33K
Function Calling
JSON Mode
InputText, Image
OutputText
in$0.1out$0.4cache$0.025–
Latency (24h)
Success Rate (24h)
GPT 4.1 is our flagship model for complex tasks. It is well suited for problem solving across domains.
Input$2
Output$8
Latency (p50)1.6s
Output Limit33K
Function Calling
JSON Mode
InputText, Image
OutputText
in$2out$8cache$0.5–