R1 0528 (free)
by DeepSeek
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/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.
Pricing
Input Tokens
Per 1M tokens
Free
Output Tokens
Per 1M tokens
Free
Image Processing
Per 1M tokens
$0.00/1M tokens
Supported Modalities
Input
text
Output
text
Performance Benchmarks
Intelligence Index
Overall intelligence score
52.0
Coding Index
Programming capability
44.1
Math Index
Mathematical reasoning
76.0
GPQA
Graduate-level questions
81.3%
MMLU Pro
Multitask language understanding
84.9%
HLE
Human-like evaluation
14.9%
LiveCodeBench
Real-world coding tasks
77.0%
AIME 2025
Advanced mathematics
76.0%
MATH 500
Mathematical problem solving
98.3%
Specifications
- Context Length
- 164K tokens
- Provider
- DeepSeek
- Released
- May 28, 2025
- Model ID
- deepseek/deepseek-r1-0528
Ready to try it?
Start chatting with R1 0528 (free) right now. No credit card required.
Start ChattingMore from DeepSeek
View all modelsCompare Models
Select a model to compare with R1 0528 (free)