Back to all models
rekaai
Reka Edge
Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...
rekaai/reka-edge
Context Size
16.384K
Input Price
615 Ks/M
Output Price
615 Ks/M
Architecture
Image
Text
Video
Supported Parameters
frequency_penaltymax_tokenspresence_penaltyseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Details
TokenizerOther
Max Completion16,384 tokens
Provider Context16.384K tokens
ModeratedNo