Max, Arena's model router powered by 5M+ community votes, is now multimodal. Starting today, Max is the default in Direct chat across every modality: search, vision, image generation, image editing, and front-end coding with the same latency-controlled performance as the original router for text. Learn more about Multimodal Max in thread.
Arena.ai Launches Multimodal Max to Automatically Route Prompts to Top Models
Arena· Updated
Arena.ai updated its intelligent model router, Max, to support multimodal tasks including vision, image generation, and front-end coding. Drawing on over 5 million community votes, the system automatically selects the most capable model for a specific prompt while maintaining low latency.
Direct chat interactions.- Community votes
- 5 million+
- Supported modalities
- Search, Vision, Image Generation, and others
- Default setting
- Direct chat
- Performance focus
- Latency-controlled
- Access
- Arena web interface
This update shifts model selection from the user to a data-driven orchestrator. Following the addition of Arena.ai's GPT-5.5 rankings and Arena's Grok 4.3 evaluation, Max now uses 5 million human preference votes to ensure users always access the current community-validated leader for their specific modality.
You can use Multimodal Max immediately through the Arena web interface. The router is designed with latency-controlled performance, matching the responsiveness of the original text-only version. It provides a unified entry point for testing frontier systems, including Poolside's Laguna coding models or DeepSeek V4 Pro's performance.
Still wondering? A few quick answers below.
Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

