DeepSeek V4 Pro review
deepseek/deepseek-v4-proDeepSeek V4 Pro is an open-weight text model built for reasoning and coding.
1.05M tokens of context — about 786,432 words, on a scale that ends at 2M.
What it can do
- Reasoning
- Tool use
- Open weights
- Takes text
- Gives text
Released 24 Apr 2026 · checked 3 Oct 2026.
About it
DeepSeek V4 Pro is a text model from DeepSeek with open weights and tool support. It can take up to 1,048,576 tokens in a conversation and produce up to 384,000 tokens in one answer. Input costs $0.2088 per million tokens and output costs $0.4176 per million tokens, with example costs ranging from fractions of a cent to about $0.42 for 1,000 chat turns.
Review
In a line
DeepSeek V4 Pro is an open-weight text model from DeepSeek. It supports reasoning and tools, and is designed for tasks including coding.
What it's good at
It supports reasoning and tool use. DeepSeek describes it as designed for advanced reasoning and coding.
It handles text input and produces text output.
Price in plain terms
Input costs $0.2088 per million tokens; output costs $0.4176 per million tokens. A token is a small piece of text the model processes or writes.
The rough costs are about 0.014 cents to read a page of about 500 words, about 0.042 cents for a chat turn with 1,000 input and 500 output tokens, and about $0.42 for 1,000 such turns.
Context and limits
It can take up to 1,048,576 tokens at once, which is the amount of text it can consider in a conversation. It can write up to 384,000 tokens in one answer.
The model is text-only: its listed inputs and outputs are text.
Ways to use it
The weights are open. Its listed identifiers are deepseek/deepseek-v4-pro and deepseek-ai/DeepSeek-V4-Pro. It supports tools. See DeepSeek models, open-weight models, and reasoning models.
Verdict
Consider it if you want an open-weight model for text-based reasoning or coding and need a very large amount of text to fit in one conversation. Its stated prices also make it possible to estimate token costs using the example figures.
Look elsewhere if your work needs image input or output; this model is listed as text-only.
Verdict
DeepSeek V4 Pro is worth considering for people choosing an open-weight text model for reasoning or coding, especially when the amount of text to consider at once matters. Its listed input and output rates, plus the sample costs, help make token spending easier to estimate. It is not a fit for tasks that need image handling, since its inputs and outputs are text. Check whether its open weights and tool support match how you plan to use a model.
- Open weights are available.
- Supports reasoning and tools.
- Can take up to 1,048,576 tokens at once.
- Can produce up to 384,000 tokens in one answer.
- Example cost is about $0.42 for 1,000 chat turns.
- Text input and output only.
- Input and output are priced separately.
- A single answer is capped at 384,000 tokens.
- Pick it ifText-based reasoning and coding tasks; People who need a large context window
- Skip it ifYou need a model that accepts or creates images.; You need more than 384,000 tokens in one answer.
Pricing
Input costs $0.2088 per million tokens and output costs $0.4176 per million tokens. The examples estimate about 0.014 cents for a page, about 0.042 cents for one chat turn, and about $0.42 for 1,000 turns.
Questions
How much does DeepSeek V4 Pro cost?
Input is $0.2088 per million tokens and output is $0.4176 per million tokens.
What does a typical chat turn cost?
A turn with about 1,000 input tokens and 500 output tokens costs about 0.042 cents.
How much text can it consider at once?
Its context window is 1,048,576 tokens.
How long can one answer be?
The maximum output is 384,000 tokens.
Can it work with images?
No image support is listed; the model takes text and produces text.
Are its weights open?
Yes. Its listed Hugging Face identifier is deepseek-ai/DeepSeek-V4-Pro.
On these boards
More from DeepSeek
- DeepSeek Flash Latest$0.015 in
- DeepSeek Pro Latest$0.13 in
- DeepSeek V4.1 Flash$0.30 in
- DeepSeek V4.1 Flash (batch)$0.11 in
- DeepSeek V4 Flash Vision Exp$0.22 in
- DeepSeek V4 Pro 0813$0.66 in
- DeepSeek V4 Flash Latest$0.009 in
- DeepSeek V4 Flash 0731$0.011 in
- DeepSeek V4 Flash 0423$0.028 in
- DeepSeek V3.2$0.28 in
- DeepSeek V3.2 Exp$0.27 in
- DeepSeek V3.1 Terminus$0.27 in
- DeepSeek V3.1$0.25 in
- R1 0528$0.50 in
- DeepSeek V3 0324$0.29 in
- R1$0.70 in
- DeepSeek V3$0.26 in