DeepSeek-V4.1-Flash pricing
$0.300 per million input tokens, $1.20 per million output tokens, 1M-token context window. A 1,500-in / 400-out request costs $0.0009.
- Input / 1M tokens
- $0.300
- Output / 1M tokens
- $1.20
- Cached input / 1M
- $0.0060
- Context window
- 1M tokens
- Max output
- 384K tokens
- Released
- —
Worked cost examples
| Workload | Per request | 1,000 requests | 6,000 requests / month |
|---|---|---|---|
| Customer-support reply (1,500 in / 400 out) | $0.0009 | $0.930 | $5.58 |
| Document summary (20,000 in / 1,000 out) | $0.0072 | $7.20 | $43.20 |
| Code review pass (8,000 in / 1,500 out) | $0.0042 | $4.20 | $25.20 |
List prices only. Caching, batch tiers and volume agreements can change these numbers substantially.
Where it sits on price
Of the 30 models in this catalog, DeepSeek-V4.1-Flash ranks 7 by output price — cheaper than 23 and more expensive than 6. Cached input is billed at $0.0060 per million tokens, about 2% of the standard input rate, so a high cache-hit rate changes the picture.
Price is not capability. A model that is half the price but needs two attempts, or that cannot hold your context, is the more expensive choice. Use these figures for budgeting and run your own evaluation for the quality decision.
Compare DeepSeek-V4.1-Flash
Price it for your own workload
Enter your real request size and traffic in the calculator to get a monthly number.
Other DeepSeek models
List price last verified Oct 15, 2026 against the vendor's published pricing. Values are peak rates. Off-peak (all hours except 01:00-04:00 and 06:00-10:00 UTC Mon-Fri) is half: $0.15 input / $0.60 output, cache-hit $0.003 per 1M.. Vendors change prices without notice — confirm on the vendor's page before you commit.