ricursiveAI's 65B dense model served in BF16, with native tool calling. 1M-token context for agent loops and long documents at a low per-token price. A preview checkpoint, so expect the weights to move.
▼Ripple 65B Preview is somewhat expensive at $0.20/M tokens input and $0.60/M tokens output. Cached input reads are priced at $0.05/M tokens, making repeated context cheaper. The model supports extended reasoning, a 1M context window.