DeepSeek-V4.1-Flash-1017

DeepSeek · open weight · deepseek-v4.1-flash-1017

DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash with the same architecture and API model name deepseek-flash. It delivers substantial gains on reasoning, coding, agentic, and visual benchmarks, with shorter task runtime and output length. It supports a 1M-token context and up to 384K output tokens. Pricing is unchanged from V4.1-Flash: peak rates are $0.30 input, $0.006 cached input, and $1.20 output per million tokens; off-peak rates are half those amounts. Peak hours are 01:00-04:00 and 06:00-10:00 UTC on weekdays, excluding Chinese public holidays. Legacy API names deepseek-v4-flash and deepseek-v4-flash-vision-exp are now served by this model.