← 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, video analysis, object detection, and agentic tool-use.
16,384 context
Modalities:text, image, video->text
Released:3/20/2026
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, video analysis, object detection, and agentic tool-use.
Weekly tokens
22.9M
Tokens generated this week (network-wide)
Rankings (last periods)
No ranking data yet for this model.