DeepSeek: DeepSeek V4.1 Flashdeepseek
Bottom Line
DeepSeek: DeepSeek V4.1 Flash: $0.02/1M input, $1.00/1M output, 1.0M context, CPS grade B. DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
API Pricing (per 1M tokens)
| Input | $0.02 |
| Output | $1.00 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.27 |
Specs & Performance
| Context Length | 1.0M |
| Max Output | 944K |
| Intelligence | 40 |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | B |
| Input / Output Modalities | text, image → text |
More from deepseek
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the DeepSeek: DeepSeek V4.1 Flash API cost?
DeepSeek: DeepSeek V4.1 Flash costs $0.02/1M input tokens and $1.00/1M output tokens. Blended cost at a 3:1 ratio is about $0.27/1M tokens.
What is the context window of DeepSeek: DeepSeek V4.1 Flash?
DeepSeek: DeepSeek V4.1 Flash supports a 1.0M token context window with up to 944K output tokens.
Is DeepSeek: DeepSeek V4.1 Flash worth it?
DeepSeek: DeepSeek V4.1 Flash has a CPS grade of B (score 63), intelligence index 40, coding index —. Use the compare page to benchmark against rivals.