Reka Edge

Tool Calling Attachments Open Weights

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,...

Providers 1

Released Mar 20, 2026

Input Modalities image, text, video

Output Modalities text

Tarsk Use coding

Available Providers (1)

Provider	Model ID	Input Cost	Output Cost	Context	Max Output	Docs
Kilo Gateway	`rekaai/reka-edge`	$0.10/MTok	$0.10/MTok	16.4K	16.4K

Capabilities

Reasoning

Tool Calling

Attachments

Open Weights

Structured Output