Violet-r1
8.41B Tokens
Search Models…
Filter
Violet-R1 is an open-source Mixture-of-Experts language model with 236 billion active parameters, optimized for math, coding, and reasoning tasks. It uses multi-stage reinforcement learning and supports up to 128K context length.
Purple 2.5 Pro
8B Tokens
Purple 2.5 Pro is Whale’s flagship multimodal “reasoning” model—able to process text, code, audio, images, and video with a massive 1 million–token context window (expanding soon to 2 million) and excels in math, science, coding, and complex reasoning benchmarks
ARCHANGEL
Search
Models