DeepSeek-V4.1-Flash-1017 by DeepSeek scores 72.5 out of 100 on the Neura Intelligence Index, ranking #72 among tracked AI models. This composite score is computed from 1 individual benchmarks across coding, math, reasoning, and language categories.

DeepSeek-V4.1-Flash-1017 costs $0.3/1M input tokens and $1.2/1M output tokens via API. At a typical 3:1 input-to-output ratio with 1M tokens/day usage, the estimated monthly cost is approximately $16.

Yes, DeepSeek-V4.1-Flash-1017 has open weights available under the mit license. You can download and self-host the model.

DeepSeek-V4.1-Flash-1017 supports a context window of 1.0 million tokens, allowing it to process very long documents, codebases, and conversations in a single request.

DeepSeek-V4.1-Flash-1017 achieves its highest score on Humanity's Last Exam with a score of 42.6%. This benchmark evaluates expert-level questions across diverse domains, designed to be the hardest public benchmark.