Mistral | Mistral Medium
Mistral Medium 3.5 is dense 128B instruction following model from Mistral AI. 262,144 token context window. Includes independent benchmarks from Artificial Analysis.
artificial-analysismanufactureraa-bootstrap
Latency
560ms
Throughput
-
Total Context
262K
Max Output
-
Input Price
$2.75/M
Output Price
$8.1/M
User Reviews
0 verified user reviews