Ministral 8B chat
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...
Capabilities
Context Window 128k tokens
Max Output 0 tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $0.11
Output $0.11
Cache Read -
Cache Write -
Supported Parameters
frequency_penaltymax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetop_p