# DeepSeek V4 Flash 0423: API price, context window and how to connect

DeepSeek V4 Flash 0423 by DeepSeek: $0.091 per million input tokens, $0.182 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 short

DeepSeek's efficient mixture-of-experts model: 284 billion parameters, 13 billion active, a 1-million-token window. Made for fast and cheap answers. The weights are open.

## Specifications

| | |
|---|---|
| Provider | [DeepSeek](https://skillok.org/docs/en/ai-models/providers/deepseek) |
| Released | 2026-04-24 |
| Context window | 1.05M tokens |
| Accepts | text |
| Answers with | text |
| Reasoning mode | yes |
| Tool calling | yes |
| Open weights | yes |
| Identifier | `deepseek/deepseek-v4-flash` |

## Price

| Per 1M tokens | In dollars |
|---|---|
| Input (question, context) | $0.091 |
| Output (answer) | $0.182 |

For reference: a conversation of 20 questions of ~500 tokens and answers of ~800 tokens costs about **$0.004**. 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

* Fast answers
* Processing large volumes of text
* An inexpensive code assistant

## 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](https://skillok.org/docs/en/ai-models/models/glm-5-3-flash) | $0.048 | $0.2 | 1.05M | 1.2× cheaper |
| [Llama 4 Scout](https://skillok.org/docs/en/ai-models/models/llama-4-scout) | $0.1 | $0.3 | 1.31M | 1.4× more expensive |
| [Llama 3.3 70B Instruct](https://skillok.org/docs/en/ai-models/models/llama-3-3-70b-instruct) | $0.1 | $0.32 | 131K | 1.5× more expensive |
| [GPT-6 Luna](https://skillok.org/docs/en/ai-models/models/gpt-6-luna) | $0.1 | $0.5 | 1.05M | 2× more expensive |
| [GPT-6 Luna Pro](https://skillok.org/docs/en/ai-models/models/gpt-6-luna-pro) | $0.1 | $0.5 | 1.05M | 2× more expensive |

## Other DeepSeek models

* [DeepSeek V4.1 Flash](https://skillok.org/docs/en/ai-models/models/deepseek-v4-1-flash)
* [DeepSeek V4 Pro 0423](https://skillok.org/docs/en/ai-models/models/deepseek-v4-pro)
* [DeepSeek V3.2](https://skillok.org/docs/en/ai-models/models/deepseek-v3-2)

## How to connect in SKILLOK

DeepSeek V4 Flash 0423 works through OpenRouter: add an OpenRouter key in **Settings → AI** and pick the `deepseek/deepseek-v4-flash` model. It then becomes available in Space AI, in tasks and to the repository agent. In detail — [Connecting a model in SKILLOK](https://skillok.org/docs/en/ai-models/connecting-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.

---

https://skillok.org/docs/en/ai-models/models/deepseek-v4-flash