Back to Models
GPT-5
Supports text, vision, thinking, tool-use, function-calling, structured-outputs
Input Modalities
text
vision
Features
thinking
tool use
function calling
structured outputs
Specifications
context window
400,000
max output tokens
128,000
Latency
5.27s
Throughput
68.20 TPS
Pricing
Pricing is based on the number of tokens used, or other metrics based on the model type.
Per 1M tokens
Input
$1.25
Output
$10.00
Other GPT models
GPT-5 mini
Supports text, vision, thinking, tool-use, function-calling, structured-outputs
GPT-4.1
Supports text, vision, tool-use, function-calling, structured-outputs
GPT-4.1 mini
Supports text, vision, tool-use, function-calling, structured-outputs
GPT-4o
Supports text, vision, audio, tool-use, function-calling, structured-outputs
GPT-4o mini
Supports text, vision, audio, tool-use, function-calling, structured-outputs
GPT OSS 120B
Supports text, thinking, function-calling, structured-outputs