Reka AI

Reka Edge

by Reka AItext+image+video->text1 endpoint

Overview

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,...

Capabilities

Text generation
Image understanding
Video understanding
Tool use / Function calling
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
ImageTextVideo
Output
Text

Technical Specifications

Context Window
16.4K tokens
Max Output
14.7K tokens
Tokenizer
Other
Uptime (24h)
10000.0%

Supported Parameters

frequency_penaltylogprobsmax_tokenspresence_penaltyseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Pricing

Per 1M tokens
Input$0.10
Output$0.10
Added
March 20, 2026
Last synced 9/19/2026