Reka releases Reka Edge, a 7B multimodal model for efficient image and video understanding

Reka has released Reka Edge, a 7-billion parameter multimodal vision-language model optimized for efficient performance on image understanding, video analysis, object detection, and agentic tool-use tasks.

Model Specifications

Reka Edge is a multimodal model that accepts image, video, and text inputs while generating text outputs. The model features:

• Parameter count: 7 billion
• Context window: 16,384 tokens
• Input pricing: $0.20 per million tokens
• Output pricing: $0.20 per million tokens
• Release date: March 20, 2026

Capabilities

According to the model documentation, Reka Edge is optimized for:

• Image understanding and analysis
• Video analysis and processing
• Object detection
• Agentic tool-use applications

The model is designed as an efficiency-focused alternative, with its 7B parameter count positioning it as a lightweight option compared to larger multimodal models.

Availability

Reka Edge is available through OpenRouter, which routes requests across multiple providers and handles normalization of requests and responses. The platform provides API access with support for various SDKs and frameworks.

The model's pricing structure—identical at $0.20 per million tokens for both input and output—simplifies cost calculation for deployment scenarios.

What this means

Reka Edge represents a focus on efficient multimodal inference, targeting use cases where model size and inference cost matter as much as capability. With a 7B parameter count and $0.20/M pricing, it positions itself as accessible for developers building vision-language applications with moderate compute constraints. The model's emphasis on video analysis and object detection suggests it's engineered for specific computer vision tasks rather than general-purpose multimodal reasoning.