← All models
R

Reka Edge

rekaai/reka-edge

VisionTool useJSONStreaming

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,...

Pricing

Input

$0.1 / 1M

Output

$0.1 / 1M

Specs

Context

16,384 tokens

Input

image, text, video

Output

text

Released: 2026-03

Supported parameters

frequency_penaltymax_tokenspresence_penaltyseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Open weights · HuggingFace

10,546 downloads/mo
131 likes
other image-text-to-text
View on HuggingFace →