deepseek-flash
Description
DeepSeek-V4.1-Flash has been upgraded to 1017. An efficient and lightweight MoE model with 284B total parameters, 13B activated, and native support for million-token ultra-long context. It features fast inference, low latency, and low invocation cost, with balanced overall capabilities. It focuses on high-concurrency and lightweight tasks, suitable for everyday conversation, content creation, basic RAG, batch copywriting, and other inclusive essential scenarios.
Specifications
- Type
- Text
- Vendor
- Deepseek
- Model ID
-
deepseek-flash - Context size
- 1M
- Max input length
- 1M
- Max output length
- 384K
- Requests per minute
- 15000
- Tokens per minute
- 1200000
Pricing
Default
Standard
Charged by input & output
- Input base price
- $0.00014286 / 1000 tokens
- Output base price
- $0.00057143 / 1000 tokens
Standard hours
00:00-09:00
18:00-00:00
12:00-14:00
Cache Hit
Standard
Charged by input
- Input base price
- $2.86E-6 / 1000 tokens
Standard hours
00:00-09:00
18:00-00:00
12:00-14:00
Default
Peak
Charged by input & output
- Input base price
- $0.00028572 / 1000 tokens
- Output base price
- $0.00114286 / 1000 tokens
Peak hours
09:00-12:00
14:00-18:00
Cache Hit
Peak
Charged by input
- Input base price
- $5.72E-6 / 1000 tokens
Peak hours
09:00-12:00
14:00-18:00
Explicit Cache Hit
Standard
Charged by input
- Input base price
- $2.86E-6 / 1000 tokens
Standard hours
00:00-09:00
18:00-00:00
12:00-14:00
Explicit Cache Hit
Peak
Charged by input
- Input base price
- $5.72E-6 / 1000 tokens
Peak hours
09:00-12:00
14:00-18:00
Default
Holiday
Charged by input & output
- Input base price
- $0.00014286 / 1000 tokens
- Output base price
- $0.00057143 / 1000 tokens
Cache Hit
Holiday
Charged by input
- Input base price
- $2.86E-6 / 1000 tokens
Explicit Cache Hit
Holiday
Charged by input
- Input base price
- $2.86E-6 / 1000 tokens