deepseek/deepseek-v4.1-flashDeepSeek V4.1 Flash is DeepSeek’s open-weights AI model, released Sep 9, 2026. It scores 156 on the Epoch Capabilities Index, costs $0.04/M input and $0.38/M output tokens, and handles a 1M-token context window. Its strongest use case is coding, where it ranks in the 75th percentile of the models Model Beat tracks.
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.
Scores on standardized evaluations. Higher is better — and rank shows where DeepSeek V4.1 Flash lands among all models tracked on Model Beat.
Abstract visual reasoning
Harder abstract reasoning
Graduate-level scientific reasoning
Frontier of human expert knowledge
Factual accuracy & hallucination
Scientific research coding
Human-rated web development
Olympiad-qualifier math
Multi-step agentic tasks
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.
DeepSeek V4.1 Flash is an AI model developed by DeepSeek, part of the DeepSeek family, released Sep 9, 2026.
DeepSeek V4.1 Flash is served from $0.04 per million input tokens and $0.38 per million output tokens (cheapest credible provider on OpenRouter: Morph).
DeepSeek V4.1 Flash supports a context window of up to 1M tokens.
On standardized evaluations tracked by Epoch AI, DeepSeek V4.1 Flash scores 1614 on WebDev Arena, 98.3% on AIME 2024/2025, 39.2% on Humanity's Last Exam.
DeepSeek V4.1 Flash is released with open weights (Open weights (unrestricted)), so the model can be downloaded and self-hosted.
Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Oct 29, 2026.