Simple, Transparent Pricing
Direct USD billing, token prices match official rates: Input $1.25/M tokens, Cached input $0.125/M tokens, Output $10/M tokens
加载中...
Usage Guide
Usage & Cost Calculation
Better understand token consumption and cost calculation
Pricing Table
Input tokens
$1.25/M tokens
Cached input tokens
$0.125/M tokens
90% off
Output tokens
$10/M tokens
The table above applies to default models like GPT-5 / GPT-5.1. For GPT-5.2, please refer to the notice below.
Important Notice: Model Pricing
GPT-5.2: GPT-5.2 model has higher official pricing: Input tokens $1.75/1M, Cached input tokens $0.18/1M, Output tokens $14.00/1M
You can view detailed token usage for each conversation in the console.
Standard Conversation Example
No cache hit, charged at standard rates
Input tokens1,000,000 tokens
Output tokens10,000 tokens
Input cost$1.250
Output cost$0.10
Total cost
$1.350
Cached Conversation Example
Most input hits cache, saving 90% on input costs
Input tokens1,000,000 tokens
Output tokens10,000 tokens
Input cost$0.125
Output cost$0.10
Total cost
$0.225