2 models
Ranked by Design Arena: asciiart
Reasoning Tools JSON Open weights 1167.0

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

deepseek/deepseek-v4-pro 2026-04-24 1.04858M context $1.6/M input $3.2/M output
62 providers
Reasoning Tools Open weights 1059.0

Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...

arcee-ai/trinity-large-thinking 2026-04-01 262.144K context $0.25/M input $0.8/M output
5 providers