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
- Provider
- Reka Edge
- Type
- Open-source / open-weight
- Modality
- text+image+video->text
- Context window
- 16,384
- Released
- March 20, 2026
Capabilities
Input: imageInput: textInput: videoOutput: text
Strengths
frequency_penaltylogprobsmax_tokenspresence_penaltyseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
More from Reka Edge
