DeepSeek: DeepSeek V3
DeepSeek V3 offers solid coding and reasoning performance at very competitive pricing with a large 163K context window, though it carries a regional accessibility penalty that limits its suitability for UK and Western businesses.
Assessment date: April 4, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Performance Profile
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models. For model details, please visit the DeepSeek-V3 repo for more information, or see the launch announcement.
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | DeepSeek |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.32 | $0.000320 |
| Output | $0.89 | $0.000890 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
