Reka Edge
All models
RekaaiRekaaiReleased 2026-03-20

Reka Edge

16K context$0.100/M input$0.100/M output7B

Reka Edge is a 7B multimodal vision-language model designed for efficient processing of image, video, and text inputs to generate text outputs. It is optimized for tasks such as image understanding, video analysis, object detection, and agentic tool-use, delivering industry-leading performance in these areas.

What is Reka Edge?

Reka Edge is an AI model from Rekaai that Agent Mag tracks for pricing, context window, modalities, benchmarks, and API compatibility. Builders can use this page to compare Reka Edge against other models for agent workflows and production deployments.

Model ID

Reka Edge is a 7B multimodal vision-language model designed for efficient processing of image, video, and text inputs to generate text outputs. It is optimized for tasks such as image understanding, video analysis, object detection, and agentic tool-use, delivering industry-leading performance in these areas.

Architecture & Specifications
Parameters
7B
Tokenizer
Other
Released
2026-03-20
Modalities
Input
imagetextvideo
Output
text
Supported Parameters
frequency_penaltymax_tokenspresence_penaltyseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Strengths
  • Efficient multimodal processing of image, video, and text inputs
  • Optimized for image understanding and video analysis
  • Industry-leading performance in object detection
  • Supports agentic tool-use
Recommended Use Cases
Image understanding
Video analysis
Object detection
Agentic tool-use

Related content

Data enriched Apr 24, 2026. Pricing from OpenRouter API.