Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length...
Rank
#455
No change
Tokens
10
2026-08-20
Requests
1
1
Tool calls
-
Input / M
$0.11
Output / M
$0.11
Cache / M
Free
Context
128K
128,000 tokens