Reka releases Reka Edge, a 7B multimodal model for efficient image and video understanding
Reka has released Reka Edge, a 7-billion parameter multimodal model designed for efficient image and video understanding. The model features a 16,384 token context window and is priced at $0.20 per million input and output tokens.
Reka Edge — Quick Specs
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.
Related Articles
Mistral AI Releases Shieldstral-1.0-3B, a 3B-Parameter Policy-Adaptive Safety Classifier
Mistral AI has released Shieldstral-1.0-3B, a compact open-weight safety classifier that evaluates text and images against natural-language policies specified at inference time. The 3B model runs on a single GPU and reports F1 scores competitive with or exceeding larger moderation models like LlamaGuard-4-12B and GPT-OSS-Safeguard-20B on multiple benchmarks.
Mistral Releases Shieldstral, a 3B Open-Weights Safety Classifier That Matches Models 7x Its Size
Mistral has released Shieldstral, a 3B open-weights safety classifier that reframes content moderation as a policy-adaptive question-answering task. The model claims to match or outperform guard models up to 7x its size on text safety and multimodal benchmarks, and runs on a single 16GB GPU.
OpenAI Halts Parts of Astra Model Development After It Hit 'Critical' Cybersecurity Threshold
OpenAI disclosed that its in-development Astra model showed cyberattack capabilities strong enough that it cannot rule out a 'Critical' risk classification. The company has paused related internal activity and added security controls under its Preparedness Framework.
Mistral's 3B-Parameter Shieldstral Matches 20B Safety Model on Text Benchmarks
Mistral's new Shieldstral, a 3-billion-parameter open-weight safety classifier, posts an 84.9% F1 score on text benchmarks—tying OpenAI's GPT-OSS-Safeguard-20B, a model roughly seven times larger. The model lets operators define safety rules at runtime using plain-language yes/no questions instead of fixed taxonomies.
Comments
Loading...