deepseek-flash (V4.1-Flash) API pricing variable pricing
deepseek-flash (V4.1-Flash) by DeepSeek costs $0.30 per 1M input tokens and $1.20 per 1M output tokens (1M in + 1M out = $1.50).
- API model id
deepseek-flash- Input / 1M
- $0.30
- Output / 1M
- $1.20
- Cached input / 1M
- $0.006
- Context window
- 1M
- Notes
- Peak price shown; off-peak is 50% cheaper.
- Source
- https://api-docs.deepseek.com/quick_start/pricing
- Provider type
- First-party (HQ: China)
- Regions
- unknown
- EU data residency
- unknown — Not stated on the pricing page.
- Last verified
- 2026-10-15
Variable pricing
The effective price of this model depends on the request. Figures above are the base (short-context / peak) tier.
- Depends on time of day: Peak price shown (01:00–04:00 and 06:00–10:00 UTC, Mon–Fri). Off-peak (all other hours, weekends, Chinese public holidays) is half: $0.15 input / $0.6 output / $0.003 cached.
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| DeepSeek | deepseek-flash (V4.1-Flash) | $0.60 |
Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.
Compare
Other DeepSeek models
- deepseek-v4-pro: $1.32 / $3.96