Model dossier

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,...

ProviderReka Start comparison

Context16,384

Max output16,384

Pricing viewTVP price

Identity

Reka Edge

Model ID: rekaai/reka-edge
Canonical slug: rekaai/reka-edge-2603
Knowledge cutoff: n/a
Created: 3/20/2026

Capabilities

imagetextvideotools

Modalities

text+image+video->textimagetextvideo

Capacity

Context16,384

Max output16,384

TokenizerOther