DeepSeek V4.1 Flash Pricing
$0.3 per 1M input and $1.2 per 1M output. Free tier: No free tier.
Cost Calculator
Estimated cost:
Full Pricing Matrix
text
| Tier | Input | Output | Unit | Cache Read |
|---|---|---|---|---|
| standard | $0.3 | $1.2 | /1M tok | $0.006 |
| off_peak | $0.15 | $0.6 | /1M tok | — |
About DeepSeek V4.1 Flash
DeepSeek-V4.1-Flash — flagship value model with 1M context, vision, thinking modes, and off-peak discounts at half price.
- Peak = standard rate; off-peak (half price) outside UTC 01:00-04:00 & 06:00-10:00 weekdays
- Cache-hit input: $0.003 off-peak / $0.006 peak per 1M
- Max output 384K; supports vision, JSON, tool calls, FIM
- Prices from api-docs.deepseek.com
Frequently Asked Questions
How much does DeepSeek V4.1 Flash cost?
Standard (peak): $0.30 per 1M input (cache miss) and $1.20 per 1M output. Off-peak hours are half price.
What is DeepSeek V4.1 Flash off-peak discount?
50% off input and output outside peak hours (UTC 01:00-04:00 and 06:00-10:00, weekdays).
Does DeepSeek Flash have a cache discount?
Yes — cache-hit input is $0.006/1M at peak (98% cheaper than cache miss).