DeepSeek V4.1 Flash
deepseek-flash, served by the DeepSeek-V4.1-Flash-1017 model, is billed with peak and off-peak pricing. Off-peak is $0.15 input / $0.003 cached / $0.60 output per 1M tokens; peak is $0.30 / $0.006 / $1.20. Peak hours are UTC Monday to Friday 01:00-04:00 and 06:00-10:00 — every other hour, including weekends and Chinese public holidays, is off-peak. Context is 1M tokens with 384K max output and a concurrency limit of 2500.
Best For
Strengths
- $0.15 off-peak input is among the lowest published input rates
- Cache hits at $0.003 off-peak, 2% of the input price
- 1M context with 384K max output
- Concurrency limit of 2500
Weaknesses
- Price doubles during UTC peak hours
- Vision support differs from the Pro model
- Legacy model names still resolve to the same endpoint
Related Alternatives
DeepSeek V4 Pro
Stronger, roughly 4.4x the off-peak price
GLM-5.3-Flash
Native multimodal at a similar price point
Frequently Asked Questions
What are the DeepSeek V4.1 Flash peak and off-peak prices?
Off-peak is $0.15 input, $0.003 cached input and $0.60 output per 1M tokens; peak is $0.30, $0.006 and $1.20. Peak hours are UTC Monday to Friday 01:00-04:00 and 06:00-10:00, excluding Chinese public holidays. All other hours, including weekends and Chinese public holidays in full, are billed at the off-peak rate.
See DeepSeek V4.1 Flash's full record in our database
Live pricing for all DeepSeek plans, token cost calculator, and the latest price changes.
View Full Comparison →