Skip to main content
RERekaai/ Reka

Reka Edge

rekaai/reka-edge-2603

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,...

Model information

Released
2026-03-20
Context window
16K
Max output
16K
Weights
Open

Modalities

Input
ImageTextVideo
Output
Text

Identity

Version
reka-edge

Resources

Capabilities

Open weightStructuredTemperatureTool call

Providers

ProviderProvider model IDProtocolContextMax outputInputOutputCapabilitiesNotesPricingStreaming
OpenRouterrekaai/reka-edgeopenai_chat16K16K
AttachmentsTool callStructuredTemperature
Hugging Face: RekaAI/reka-edge-2603
input $0.1/M · output $0.1/M
Yes
Kilo Gatewayrekaai/reka-edgeopenai_chat16K16K
AttachmentsTool callStructuredTemperature
-
input $0.1/M · output $0.1/M
Yes
Rekareka-edgecustom16K16K
---Yes

FAQ