Features
Resources
Pricing
Back to Models
GPT-5 mini
Supports text, vision, thinking, tool-use, function-calling, structured-outputs
Input Modalities
text
vision
Features
thinking
tool use
function calling
structured outputs
Pricing
Pricing is based on the number of tokens used, or other metrics based on the model type.
Per 1M tokens
Input
$0.25
Output
$2.00
Cached input
$0.03
Specifications
context window
400,000
max output tokens
128,000
Latency
5.95s
Throughput
57.24 TPS
