DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 is a large language model made by DeepSeek, added to the catalog on 24 Apr 2026. It has a context window of 1,048,576 tokens and costs $0.90 per 1M input tokens and $1.50 per 1M output tokens. It accepts text and produces text. Typical uses: reasoning over long documents, working with extensive code inputs and drafting code-related responses.
Price checked ยท source: OpenRouter
What DeepSeek V4 Pro 0423 is
DeepSeek V4 Pro 0423 is a text-in, text-out model from DeepSeek. The catalog identifies it as a large-scale Mixture-of-Experts model with 1.6 trillion total parameters and 49 billion activated parameters. It is designed for advanced reasoning and coding. The model supports reasoning, tools, structured outputs, and response-format controls. Its documented input and output modality is text, so the catalog does not describe image or audio input or output. These capabilities make it relevant to tasks that involve analyzing or producing written material, including code and responses that need a defined structure.
The model has a context window of 1,048,576 tokens and a maximum output of 393,216 tokens. Its large context capacity suits work involving substantial text in one prompt, such as reviewing long documents, examining sizeable code inputs, or following extended technical discussions. The maximum output also allows for lengthy generated text when a task requires it. Tool support can be used in workflows that involve tools, while structured outputs and response-format controls provide options for shaping the form of a response. The catalog does not specify particular tools or output formats, so those details depend on the application using the model. Overall, its documented focus and capabilities suit reasoning and coding tasks that work with large amounts of text and may call for organized responses.
Key features
- Accepts text and produces text
- Supports a context window of 1,048,576 tokens
- Supports up to 393,216 output tokens
- Supports reasoning, tools, and structured outputs
- Supports response-format controls
Typical uses
- Reasoning over long documents
- Working with extensive code inputs
- Drafting code-related responses
- Producing structured text responses
DeepSeek V4 Pro 0423 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.90 |
| Output, per 1M tokens | $1.50 |
| Cached input read, per 1M tokens | $0.20 |
No price change since it was added on 24 Apr 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0009 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.024 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.030 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.137 |
DeepSeek V4 Pro 0423 specifications
| Model id | deepseek/deepseek-v4-pro |
|---|---|
| Version | deepseek-v4-pro-20260423 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 393,216 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 24 Apr 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for DeepSeek V4 Pro 0423 yet.
Compare DeepSeek V4 Pro 0423
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.