DeepSeek V4.1 Flash: API price, context window and how to connect
DeepSeek V4.1 Flash by DeepSeek: $0.044 per million input tokens, $0.08 per million output tokens, a 1.05M-token window. What it is good for, what to compare it with and how to connect it in SKILLOK.
In this article
In short#
DeepSeek's sparse mixture-of-experts model, the first on the Causal Encoder-Decoder architecture. The weights are open, and the price is one of the lowest in the catalog.
Specifications#
| Provider | DeepSeek |
| Released | 2026-09-10 |
| Context window | 1.05M tokens |
| Accepts | text, images |
| Answers with | text |
| Reasoning mode | yes |
| Tool calling | yes |
| Open weights | yes |
| Identifier | deepseek/deepseek-v4.1-flash |
Price#
| Per 1M tokens | In dollars |
|---|---|
| Input (question, context) | $0.044 |
| Output (answer) | $0.08 |
For reference: a conversation of 20 questions of ~500 tokens and answers of ~800 tokens costs about $0.002. Models in reasoning mode spend more tokens on an answer than the text shows: the reasoning is paid for too.
What it is good for#
- A high volume of simple tasks almost for free
- Drafts of text and code
- Running on your own servers
Similar models#
Catalog models with the same kind of output, closest in the price of a typical request.
| Model | Input | Output | Window | Price |
|---|---|---|---|---|
| GLM 5.3 Flash | $0.048 | $0.2 | 1.05M | 1.9× more expensive |
| DeepSeek V4 Flash 0423 | $0.091 | $0.182 | 1.05M | 2.2× more expensive |
| Llama 4 Scout | $0.1 | $0.3 | 1.31M | 3.1× more expensive |
| Llama 3.3 70B Instruct | $0.1 | $0.32 | 131K | 3.2× more expensive |
| GPT-6 Luna | $0.1 | $0.5 | 1.05M | 4.5× more expensive |
Other DeepSeek models#
How to connect in SKILLOK#
DeepSeek V4.1 Flash works through OpenRouter: add an OpenRouter key in Settings → AI and pick the deepseek/deepseek-v4.1-flash model. It then becomes available in Space AI, in tasks and to the repository agent. In detail — Connecting a model in SKILLOK.
Where the data comes from#
Prices, the context window and capabilities come from the public OpenRouter catalog as of 2026-10-19. A provider may change the price — the exact figure is always on the model's OpenRouter page.
Was this helpful?