Skip to content
Vercel April 2026 security incident
Read the bulletin
All Models

DeepSeek R1 0528

deepseek/deepseek-r1

DeepSeek R1 0528 is DeepSeek's open-source reasoning model, released January 20, 2025. It scores 79.8% Pass@1 on AIME 2024 and 97.3% on MATH-500. Weights ship under the MIT License for commercial use.

ReasoningImplicit Caching
index.ts
import { streamText } from 'ai'


const result = streamText({
  model: 'deepseek/deepseek-r1',
  prompt: 'Why is the sky blue?'
})

What To Consider When Choosing a Provider

  • Zero Data Retention

    AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.

    Authentication

    AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

DeepSeek R1 0528 generates verbose reasoning traces before final answers. Budget output tokens generously and account for variable response length when estimating costs.

When to Use DeepSeek R1 0528

Best For

  • Competitive mathematics:

    Formal proof construction and quantitative reasoning where AIME 2024 and MATH-500 benchmark results match your task

  • Code generation and debugging:

    Algorithm design where RL-derived problem-solving patterns produce self-correcting chains before final output

  • Complex analytical reasoning:

    Multi-step reasoning in finance, science, and engineering where showing work and self-verification build trust

Consider Alternatives When

  • Conversation or summarization:

    Extended reasoning traces add unnecessary output token cost for content generation workloads

  • Hybrid thinking modes:

    DeepSeek-V3.1 or later supports both thinking and non-thinking modes through the same endpoint

  • Strict latency requirements:

    Variable response times from long reasoning chains are not acceptable when latency is a hard constraint

  • Pure creative writing:

    Structured reasoning adds no quality benefit for open-ended generation tasks

Conclusion

DeepSeek R1 0528 matches closed-source models on published benchmarks while shipping weights under the MIT License. For math, code, and formal reasoning workloads, it fits teams that need open weights.

FAQ

DeepSeek applied reinforcement learning directly to the base model, bypassing the conventional step of training on human-written reasoning traces. Reasoning patterns like self-verification and reflection emerged from RL exploration rather than curated data.

79.8% Pass@1 on AIME 2024, on par with OpenAI o1 at release. On MATH-500 it scores 97.3%.

The MIT License permits commercial use. Many proprietary reasoning models impose stricter restrictions.

A context window of 160K tokens. The architecture is Mixture-of-Experts (MoE) with 671B total parameters, activating 37B per forward pass.

DeepSeek R1 0528 specializes in deep reasoning with extended chain-of-thought. DeepSeek-V3 and later variants are general-purpose models that balance reasoning with faster, lower-cost completions and suit mixed-workload deployments better.

Yes. The chain-of-thought trace appears in the response. This helps with debugging and with applications that display the model's reasoning to end users.