R1 0528
DeepSeek R1 0528 is a large-scale open-source model released on May 28, 2025. It is designed for complex reasoning tasks and supports tool calling, offering performance comparable to OpenAI's o1 model.
R1 0528 specs and pricing
- Provider: DeepSeek
- Released: May 28, 2025
- Context window: 164K tokens
- Max output: 32K tokens
- Input: text
- Output: text
- Price: $0.57 input / $2.29 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What R1 0528 is good at
- Complex logical reasoning tasks
- Projects requiring open-source transparency
- Workflows that benefit from integrated tool calling
To-dos to try with R1 0528
- Analyze a complex technical document and explain the underlying logic step-by-step
- Use tool calling to retrieve current data and synthesize it into a structured report
- Solve a multi-step mathematical or programming problem while showing the reasoning process
FAQ
- What is the primary focus of the DeepSeek R1 0528 model? The model is specifically designed for advanced reasoning capabilities and provides full transparency into its reasoning tokens.
- Does this model support external tools? Yes, DeepSeek R1 0528 includes built-in support for tool calling.
- How much does R1 0528 cost? R1 0528 costs $0.57 per million input tokens and $2.29 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.92 credits ($1 = 100 credits).
- What is the context window of R1 0528? R1 0528 can read up to 164K tokens at once and write up to 32K tokens in one reply.
- Can I use R1 0528 without coding? Yes. In todo.is you pick R1 0528 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.