Mistral Large 3 2512 chat
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
Capabilities
Context Window 262k tokens
Max Output 0 tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $0.50
Output $1.50
Cache Read $0.05
Cache Write -
Supported Parameters
frequency_penaltymax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p