Model Square
OpenAI

gpt-6-astra

OpenAI·Usage-based billing
TPS
Average latency
Success rate

Pricing

Base Price

Input
$10/ 1M
Output
$50/ 1M
Cached input$1/ 1M
Cache write$12.5/ 1M

Pricing by Group

GroupRatioInputOutputCacheCache Write
default
2x
$20
$100
$2
$25

Prices shown per 1M tokens

Model

ProviderOpenAI
TypeUsage-based billing
Groups
default
Endpoints
openai
gpt-6-astra