DeepSeek: DeepSeek V4 Pro 0423
8.7 / 10
1M context
Proprietary
About this model
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Benchmark Scores
MMLU-Pro
87.5
LiveCodeBench
93.5
SWE-Bench-Verified
80.6
Terminal-Bench-2.1
87.9
Technical Specs
- Architecture: text->text
- Context Window: 1,048,576 tokens
- Input Modalities: text
Hardware Requirements
- API-only (no local hardware needed)
Pricing
| Input | Output | Currency |
|---|---|---|
| 1.6 / 1M tokens | 3.1999999999999997 / 1M tokens | USD |