ricursiveAI's 65B dense model served in BF16, with native tool calling.
DeepSeek's October 2026 checkpoint of the V4.1 Flash workhorse, refreshed for stronger agentic coding with shorter, faster answers.
No shared demos for these models yet.
No captured outputs for these models yet.
Both Ripple 65B Preview and DeepSeek V4.1 Flash 1017 are capable AI models. The best choice depends on your specific use case: consider pricing, context window, speed, and which capabilities (vision, reasoning, audio) you need.
DeepSeek V4.1 Flash 1017 has a lower blended cost. Ripple 65B Preview: $0.20 input / $0.60 output. DeepSeek V4.1 Flash 1017: $0.006 input / $0.50 output.
Ripple 65B Preview has a larger context window: Ripple 65B Preview supports 1M tokens vs DeepSeek V4.1 Flash 1017 at 1M tokens.
DeepSeek V4.1 Flash 1017 supports vision/image input, but Ripple 65B Preview does not.
Key differences: DeepSeek V4.1 Flash 1017 is significantly cheaper; only DeepSeek V4.1 Flash 1017 supports vision input. Compare full specs on this page.
If cost is your priority, choose the cheaper option. If you need the highest intelligence for complex tasks, pick the higher-scoring model. For long documents or codebases, choose the larger context window. You can try both Ripple 65B Preview and DeepSeek V4.1 Flash 1017 for free on idapt.app to see which performs better for your specific needs.