ThePromptBuddy logoThePromptBuddy

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,...

Specifications
ProviderRekaai
Input pricing$0.10/M tokens
Output pricing$0.10/M tokens
Context length16K tokens
Max output16K tokens
Input modalities
imagetextvideo
Output modalities
text
TokenizerOther
Content moderatedNo
HuggingFaceRekaAI/reka-edge-2603

Supported Parameters

frequency_penaltylogprobsmax_tokenspresence_penaltyseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p