DeepSeek: R1
DeepSeek R1 is one of the stronger open reasoning models available, with impressive scores across math, coding, and GPQA benchmarks at a very competitive price point. However, limited Western API support and data compliance considerations make it less straightforward for UK businesses compared to equivalent models from established Western providers.
Assessment date: March 12, 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
DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model & technical report. MIT licensed: Distill & commercialize freely!
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | DeepSeek |
| Instruct Type | deepseek-r1 |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.70 | $0.000700 |
| Output | $2.50 | $0.002500 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
