ML
Input
$0.10/MTok
Output
$0.10/MTok
Specifications
Context Window
128K context
Max Output
8K tokens
Caching
No
Batch API
No
Vision
No
Tool Use
Supported
Cost Examples
Single chat message
500 input + 300 output tokens
$0.000080/request
Code review
5,000 input + 2,000 output tokens
$0.000700/request
Document summary
50,000 input + 1,000 output tokens
$0.0051/request
100 requests/day
1,000 input + 500 output × 30 days
$0.45/month