Back to all models
mistralai
mistralaiMistral: Pixtral 12B
The first multi-modal, text+image-to-text model from Mistral AI. Its weights were launched via torrent: https://x.com/mistralai/status/1833758285167722836.
mistralai/pixtral-12b
Context Size
32.768K
Input Price
615 Ks/M
Output Price
615 Ks/M
Architecture
Text
Image
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyseedstoptemperaturetop_ktop_p
Details
TokenizerMistral
Provider Context32.768K tokens
ModeratedNo