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,...
The figures
- Made by
- rekaai
- Model ID
- rekaai/reka-edge
- Input
- $0.1 per million tokens
- Output
- $0.1 per million tokens
- Context window
- 16K tokens
- Longest answer
- 15K tokens
- Takes in
- image, text, video
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- Yes
- Open weights
- Yes
- Released
- 20 Mar 2026
Read on 3 Oct 2026.