Model Price Index
Updated 2026-08-04 · Changelog

Ministral 8B

AWS Bedrock

Mistral's compact 8B model on Bedrock for cost-efficient, low-latency text processing at scale

$0.15

Input

$0.15

Output

per 1M tokens

Ratesper 1M tokens

Input$0.15
Output$0.15

Estimate Your Monthly Cost

A request with input and output tokens, requests / month at a % cache hit rate $9.75/mo

Compare all models at this workload →

Excludes cache writes and batch discounts.