Reka AI
Reka Edge
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.
Input
$0.1
/ 1M tokens
Output
$0.1
/ 1M tokens
Context window
16.38K
tokens
Limits
Context
16,384
tokens
Max output
14,745
90% of the context window
Parameters
7,128,509,568
Model facts
Author
Reka AI
Tokenizer
Other
Modality
Text + Image + Video -> Text
License
Other
Created
Mar 20, 2026
Hugging Face
RekaAI/reka-edge-2603
Publication status
Hugging Face: verifiedLicense: publishedParameter count: published
Modalities
Input · ImageInput · TextInput · VideoOutput · Text
Generation controls
Frequency penaltyLogprobsMax tokensPresence penaltySeedStopStructured outputsTemperatureTool choiceToolsTop kTop logprobsTop p