AI Radar
Support
LiveUpdated 2026-11-06 15:10 UTC

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash — DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first…

DeepSeek V4.1 Flash is DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. $0.035 per million input tokens, $0.29 per million output tokens.…. It is ranked #7665 on the AI Radar, in AI infra & evals, first seen 50 days ago and shared in 1 post (3.4k views).

Visit openrouter.ai

DeepSeek V4.1 Flash - API Pricing & Benchmarks | OpenRouter Benchmarks Chat Pricing Docs Sign Up Sign Up DeepSeek: DeepSeek V4.1 Flash deepseek / deepseek-v4.1-flash Model weights Compare API Try this model DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start…

Alternatives to DeepSeek V4.1 Flash

DeepSeek V4.1 Flash in numbers

FAQ

What is DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. $0.035 per million input tokens, $0.29 per million output tokens.… It was first shared on X 50 days ago and is ranked #7665 on the AI Radar.

Is DeepSeek V4.1 Flash free?

It is a paid product.

Who shared DeepSeek V4.1 Flash?

1 account on X, including @vipulved, in 1 post totalling 3.4k views.

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.