deepseek
DeepSeek: DeepSeek V4 Pro
DeepSeek V4 Pro, developed by DeepSeek, is equipped with a context length of 1,048,576 tokens and supports text input only. It excels in both reasoning tasks and tool integration, making it suitable for complex problem-solving scenarios. The model’s benchmark blended score of 82.3 across four independent tests indicates strong performance, especially in AI Index Coding with a score of 97.9. Given its pricing at $0.435 per million input tokens and $0.87 per million output tokens, DeepSeek V4 Pro is cost-effective for projects requiring both extensive context handling and advanced reasoning capabilities.
Quality Score
99/100
price + capability + benchmarks
Input Price
$0.43
per 1M tokens
Output Price
$0.87
per 1M tokens
Context Window
1,048,576
tokens
Benchmark results
Independent, published benchmarks. Blended score 82.3 across 4 benchmarks, last refreshed 2026-07-23. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 73.1 |
| AI Index Coding | software engineering tasks | 97.9 |
| AI Index Agentic | multi-step tool-using tasks | 60.0 |
| EQ-Bench | emotional understanding in dialogue | 77.6 |
- Model ID
- deepseek/deepseek-v4-pro
- Vendor
- deepseek
- Released
- April 2026
- Tokenizer
- DeepSeek
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 384,000 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.43/M input and $0.87/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.26 |
| A month of a busy support chatbot | 5M in / 2M out | $3.92 |
Strong choice for
Code
SQL Generation
Writing correct, performant SQL from natural-language prompts.
Code
Code Completion
Inline IDE-style autocomplete that has to feel instant.
Code
Code Documentation
Writing clear docstrings and READMEs that match the code.
Code
Regex Writing
Crafting regular expressions that actually match what you intend.
Code
CI/CD Pipelines
Authoring GitHub Actions, GitLab CI, and CircleCI configs.
Data
CSV / Spreadsheet Cleanup
Normalizing messy tabular data with consistent fields.
Category rankings
Where DeepSeek: DeepSeek V4 Pro places across the 63 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #2 | Code CompletionCode · of 25 ranked | 134 |
| #2 | Code DocumentationCode · of 25 ranked | 147 |
| #2 | Short-Form SummarizationWriting · of 25 ranked | 132 |
| #2 | Email DraftingWriting · of 25 ranked | 128 |
| #2 | Transcript CleanupWriting · of 25 ranked | 146 |
| #2 | Language LearningEducation · of 25 ranked | 128 |
| #2 | Chat CompanionPersonal · of 25 ranked | 132 |
| #2 | Trivia & General KnowledgePersonal · of 25 ranked | 122 |
| #3 | Regex WritingCode · of 25 ranked | 137 |
| #3 | Language TranslationWriting · of 25 ranked | 137 |
| #3 | Customer SupportBusiness · of 25 ranked | 133 |
| #3 | Sales / Cold EmailBusiness · of 25 ranked | 124 |
| #3 | Meeting NotesBusiness · of 25 ranked | 157 |
| #3 | Job Application DraftingBusiness · of 25 ranked | 124 |
| #3 | Journaling HelperPersonal · of 25 ranked | 124 |
| #3 | Recipe GenerationPersonal · of 25 ranked | 124 |
| #3 | Tutoring for KidsPersonal · of 25 ranked | 137 |
| #3 | Dataset AnnotationResearch · of 25 ranked | 143 |
| #4 | CSV / Spreadsheet CleanupData · of 25 ranked | 157 |
| #4 | JSON ExtractionData · of 25 ranked | 147 |
| #4 | Resume WritingBusiness · of 25 ranked | 118 |
| #5 | SQL GenerationCode · of 25 ranked | 172 |
| #5 | CI/CD PipelinesCode · of 25 ranked | 146 |
| #5 | Bulk Data LabelingData · of 25 ranked | 134 |
| #5 | Long-Document SummarizationWriting · of 25 ranked | 166 |
| #5 | Blog Post WritingWriting · of 25 ranked | 142 |
| #5 | Marketing CopyWriting · of 25 ranked | 131 |
| #5 | Standardized Test PrepEducation · of 25 ranked | 131 |
| #5 | Character RoleplayPersonal · of 25 ranked | 154 |
| #5 | Trip PlanningPersonal · of 25 ranked | 142 |
| #6 | Code ReviewCode · of 25 ranked | 171 |
| #6 | Code RefactoringCode · of 25 ranked | 170 |
| #6 | ETL ScriptingData · of 25 ranked | 158 |
| #6 | Creative WritingWriting · of 25 ranked | 161 |
| #6 | Screenwriting & DialogWriting · of 25 ranked | 161 |
| #6 | Academic WritingWriting · of 25 ranked | 161 |
| #6 | Legal DraftingProfessional · of 25 ranked | 161 |
| #6 | Legal ResearchProfessional · of 25 ranked | 173 |
| #6 | Contract ReviewProfessional · of 25 ranked | 183 |
| #6 | Medical Note SummarizationProfessional · of 25 ranked | 158 |
| #6 | Scientific ResearchProfessional · of 25 ranked | 173 |
| #6 | Physics TutoringEducation · of 25 ranked | 150 |
| #6 | History TutoringEducation · of 25 ranked | 148 |
| #6 | Essay GradingEducation · of 25 ranked | 171 |
| #6 | RFP ResponseBusiness · of 25 ranked | 179 |
| #6 | OKRs & Strategic PlanningBusiness · of 25 ranked | 161 |
| #6 | RAG PipelinesAgents · of 25 ranked | 170 |
| #6 | Long-Context Q&AAgents · of 25 ranked | 160 |
| #6 | Fiction CollaboratorPersonal · of 25 ranked | 173 |
| #6 | Math ProofsResearch · of 25 ranked | 161 |
| #6 | Literature ReviewResearch · of 25 ranked | 173 |
| #7 | Bug FixingCode · of 25 ranked | 182 |
| #7 | Unit Test GenerationCode · of 25 ranked | 156 |
| #7 | Agent WorkflowsAgents · of 25 ranked | 193 |
| #7 | Coding AgentsAgents · of 25 ranked | 193 |
| #7 | Scientific CodingResearch · of 25 ranked | 182 |
| #10 | Math TutoringEducation · of 25 ranked | 147 |
| #10 | SOP / Process DocsBusiness · of 25 ranked | 137 |
| #10 | Experiment DesignResearch · of 25 ranked | 157 |
| #11 | Data AnalysisData · of 25 ranked | 168 |
| #11 | Financial AnalysisProfessional · of 25 ranked | 158 |
| #11 | Fitness CoachingPersonal · of 25 ranked | 134 |
| #12 | Function / Tool CallingAgents · of 25 ranked | 149 |
Similar models
deepseek
DeepSeek: DeepSeek V4 Flash
$0.10 in / $0.20 out
1,048,576 ctx
99
deepseek
DeepSeek: DeepSeek V3.2
$0.27 in / $0.40 out
163,840 ctx
95
deepseek
DeepSeek: DeepSeek V3.2 Exp
$0.27 in / $0.41 out
163,840 ctx
95
deepseek
DeepSeek: DeepSeek V3.1
$0.25 in / $0.95 out
163,840 ctx
94
deepseek
DeepSeek: DeepSeek V3.1 Terminus
$0.27 in / $1.00 out
163,840 ctx
94
deepseek
DeepSeek: R1 0528
$0.50 in / $2.15 out
163,840 ctx
94
Quick answers
- How much does DeepSeek: DeepSeek V4 Pro cost?
- $0.43 per million input tokens and $0.87 per million output tokens.
- What is DeepSeek: DeepSeek V4 Pro's context window?
- 1,048,576 tokens, roughly 1,572 pages of text in a single request.
- Does DeepSeek: DeepSeek V4 Pro support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can DeepSeek: DeepSeek V4 Pro process images?
- No, it is text-only on the input side.