Model Square
Qwen

qwen3.8-flash

阿里巴巴·Usage-based billing
TPS
Average latency
Success rate

Pricing

Base Price

Input
$0.1194/ 1M
Output
$0.403/ 1M
Cached input$0.0149/ 1M

Pricing by Group

GroupRatioInputOutputCache
default
1x
$0.1194
$0.403
$0.0149

Prices shown per 1M tokens

Model

Provider阿里巴巴
TypeUsage-based billing
Groups
default
Endpoints
openai
qwen3.8-flash