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

DeepSeek V4 Pro 0423 by DeepSeek: $0.955 per million input tokens, $1.911 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.

Updated Copy as Markdown
In this article

In short#

DeepSeek's large mixture-of-experts model: 1.6 trillion parameters, 49 billion active, a 1-million-token window. Built for hard reasoning, code and agentic tasks. The weights are open.

Specifications#

Provider 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-pro

Price#

Per 1M tokens In dollars
Input (question, context) $0.955
Output (answer) $1.911

For reference: a conversation of 20 questions of ~500 tokens and answers of ~800 tokens costs about $0.04. 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#

  • Reasoning and code for little money
  • Long documents whole
  • Deploying it yourself

Similar models#

Catalog models with the same kind of output, closest in the price of a typical request.

Model Input Output Window Price
Mistral Large 4 $0.68 $2.09 1.05M about the same
Devstral 2 2512 $0.4 $2 262K 1.3× cheaper
Kimi K2.7 Code $0.671 $3.35 262K 1.3× more expensive
Qwen3.8 27B $0.24 $2.2 1M 1.3× cheaper
Grok 4.3 $1.25 $2.5 1M 1.3× more expensive

Other DeepSeek models#

How to connect in SKILLOK#

DeepSeek V4 Pro 0423 works through OpenRouter: add an OpenRouter key in Settings → AI and pick the deepseek/deepseek-v4-pro 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?