Reka Edgeon Krater.ai
Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs.
Released March 20, 2026
Specifications
Reka Edge at a glance
Context
16.4K tokens
Max output
16.4K tokens
Input
Image, Text, Video
Output
Text
Input price
$0.10 / 1M
Output price
$0.10 / 1M
Capabilities
What it is good at
Catalog capabilities
- Accepts image input
- Generates text responses
- Supports tool calling
- Supports structured outputs
Good for
Compare
Compare Reka Edge
Reka Edge vs Reka Flash 3
Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka.
Open comparisonReka Edge vs Gemma 4 26B A4B
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Open comparisonReka Edge vs Gemma 4 26B A4B (free)
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Open comparisonFAQ
Questions about Reka Edge
Clear answers based on the model catalog and Krater access.
Use Reka Edge in your API
Connect with Krater's unified API.