# DeepSeek-R1-0528

> DeepSeek's open-weight R1 upgrade with deeper reasoning, fewer hallucinations, and function calling — AIME 2025 up from 70 to 87.5.

- Maker: DeepSeek
- Line: DeepSeek R1
- Canonical page: https://ai-tldr.dev/models/deepseek-r1-0528/
- Updated: 2026-06-18

## In short

DeepSeek-R1-0528 is the May 28, 2025 update to DeepSeek's first-generation reasoning line, DeepSeek R1. It has a 164K-token context window and costs $0.50 per million input tokens and $2.15 per million output tokens. You can use it through DeepSeek Platform and OpenRouter.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 164K (max output 32K tokens (64K max generation length)) | [1] |
| Input price | $0.50 / 1M tokens | [2] |
| Output price | $2.15 / 1M tokens | [2] |
| Licence | MIT · open weights | [1] |
| Released | 28 May 2025 | [3] |
| Parameters | 671B total / 37B active (685B on Hugging Face incl. MTP module) | [1] |
| Knowledge cutoff | Not officially disclosed | [1] |

## Sources

1. [DeepSeek-R1-0528 — Hugging Face model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528)
2. [OpenRouter — R1 0528 pricing & benchmarks](https://openrouter.ai/deepseek/deepseek-r1-0528)
3. [DeepSeek — official site](https://www.deepseek.com)

## Overview

DeepSeek-R1-0528 is the May 28, 2025 update to DeepSeek's first-generation reasoning line, DeepSeek R1. Like the original R1, it is a Mixture-of-Experts model built on the DeepSeek-V3 base — 671 billion total parameters with roughly 37 billion active per token (the Hugging Face card lists 685B, which includes the multi-token-prediction module). It is released as open weights under the permissive MIT license, which allows commercial use and distillation.

The 0528 revision is a same-architecture refresh rather than a new model: DeepSeek added post-training compute and algorithmic optimizations that deepen the model's reasoning. Average reasoning length per question roughly doubled (about 12K to 23K tokens on AIME), and benchmark scores jumped accordingly — AIME 2025 rose from 70.0 to 87.5, AIME 2024 from 79.8 to 91.4, and LiveCodeBench from 63.5 to 73.3. DeepSeek also reports a reduced hallucination rate, native support for JSON output and function calling, and system-prompt support, with no need to prepend a thinking tag to trigger reasoning.

DeepSeek-R1-0528 has a 163,840-token (about 164K) context window and is text-only — no vision, audio, or PDF input. Alongside the flagship, DeepSeek distilled its chain-of-thought into a small model, DeepSeek-R1-0528-Qwen3-8B (fine-tuned on Qwen3-8B Base), which reaches 86.0 on AIME 2024 — state-of-the-art among open 8B models. The weights are on Hugging Face and the hosted API exposes the model as deepseek-reasoner; it was positioned as an open challenger to OpenAI o3 and Gemini 2.5 Pro.

## Benchmarks

- AIME 2024 (Pass@1): 91.4% ([source](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528))
- AIME 2025 (Pass@1): 87.5% ([source](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528))
- HMMT 2025 (Pass@1): 79.4% ([source](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528))
- CNMO 2024 (Pass@1): 86.9% ([source](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528))
- GPQA Diamond (Pass@1): 81% ([source](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528))
- Humanity's Last Exam (Pass@1): 17.7% ([source](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528))
- LiveCodeBench (Pass@1): 73.3% ([source](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528))
- Codeforces Rating: 1930 ([source](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528))
- SWE Verified (Resolved): 57.6% ([source](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528))
- Aider-Polyglot: 71.6% ([source](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528))
- MMLU-Pro (EM): 85% ([source](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528))
- MMLU-Redux (EM): 93.4% ([source](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528))
- FRAMES (Acc.): 83% ([source](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528))

## Pricing

- Input: $0.50 / 1M tokens per 1M tokens
- Output: $2.15 / 1M tokens per 1M tokens

Standard OpenRouter rate for the open-weight DeepSeek-R1-0528. Other hosts price it differently (Artificial Analysis lists a $1.35 in / $4.20 out provider). DeepSeek's first-party API serves it as deepseek-reasoner; that endpoint's current pricing now reflects a newer model, so the OpenRouter figure is cited here.

Source: https://openrouter.ai/deepseek/deepseek-r1-0528

## Strengths

- Open weights under the permissive MIT license — free for commercial use, self-hosting, and distillation
- Large gains in deep reasoning over the original R1: AIME 2025 87.5 (up from 70.0), AIME 2024 91.4, HMMT 2025 79.4
- Strong competition math and coding — Codeforces rating ~1930, LiveCodeBench 73.3, Aider-Polyglot 71.6
- Reduced hallucination rate versus the original R1, per DeepSeek
- Native JSON output and function-calling support, plus system-prompt support without a manual thinking tag
- Distilled DeepSeek-R1-0528-Qwen3-8B brings R1-grade reasoning to commodity hardware (86.0 on AIME 2024)

## Best for

- Competition-style math and multi-step logical reasoning
- Coding and software-engineering tasks (LiveCodeBench, SWE-bench, Aider-style edits)
- Agentic tool use and function-calling workflows that need structured JSON output
- Self-hosted reasoning deployments where an open MIT-licensed model is required
- Distillation: using R1-0528's chain-of-thought to train smaller, cheaper student models

## How to access

- [DeepSeek Platform](https://api-docs.deepseek.com/) — model id `deepseek-reasoner`
- [OpenRouter](https://openrouter.ai/deepseek/deepseek-r1-0528) — model id `deepseek/deepseek-r1-0528`

## DeepSeek R1 versions

- DeepSeek-R1-0528 (28 May 2025): Deeper reasoning, fewer hallucinations, JSON + function calling — this page
- [DeepSeek-R1](https://ai-tldr.dev/models/deepseek-r1/) (20 January 2025): First-gen reasoning model, comparable to OpenAI o1
- [DeepSeek-R1-Zero](https://ai-tldr.dev/models/deepseek-r1-zero/) (20 January 2025): RL-only reasoning model with no SFT cold start

## FAQ

### What changed in DeepSeek-R1-0528 versus the original DeepSeek-R1?

DeepSeek-R1-0528 keeps the same Mixture-of-Experts architecture on the V3 base but adds post-training compute and algorithmic tuning that deepen its reasoning. Per-question reasoning roughly doubled (about 12K to 23K tokens on AIME), and scores rose across the board — AIME 2025 from 70.0 to 87.5, AIME 2024 from 79.8 to 91.4, and LiveCodeBench from 63.5 to 73.3. DeepSeek also reports fewer hallucinations and added JSON output and function-calling support.

### Is DeepSeek-R1-0528 open source and free to use?

The weights are released under the MIT license on Hugging Face, so you can download, self-host, fine-tune, distill, and use them commercially for free. DeepSeek also offers a hosted API (where the model is exposed as deepseek-reasoner), and several third parties such as OpenRouter serve it for a per-token fee.

### How big is DeepSeek-R1-0528 and what is its context window?

It is a Mixture-of-Experts model with 671 billion total parameters and about 37 billion active per token (the Hugging Face card lists 685B, which includes the multi-token-prediction module). Its context window is 163,840 tokens — roughly 164K — and it is text-only.

### What is DeepSeek-R1-0528-Qwen3-8B?

It is a small distilled model released alongside the flagship: DeepSeek used chain-of-thought from DeepSeek-R1-0528 to post-train Qwen3-8B Base. It scores 86.0 on AIME 2024 — state-of-the-art among open-source 8B models and, per DeepSeek, comparable to the much larger Qwen3-235B-thinking. It is also MIT-licensed.

## Links

- [DeepSeek — official site](https://www.deepseek.com)
- [DeepSeek-R1-0528 — Hugging Face model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528)
- [DeepSeek-R1-0528-Qwen3-8B — distilled model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B)
- [DeepSeek-R1 paper (arXiv 2501.12948)](https://arxiv.org/abs/2501.12948)
- [DeepSeek API docs (deepseek-reasoner)](https://api-docs.deepseek.com/)
- [OpenRouter — R1 0528 pricing & benchmarks](https://openrouter.ai/deepseek/deepseek-r1-0528)
- [Artificial Analysis — DeepSeek R1 0528 analysis](https://artificialanalysis.ai/models/deepseek-r1)
- [VentureBeat — R1-0528 launch coverage](https://venturebeat.com/ai/deepseek-r1-0528-arrives-in-powerful-open-source-challenge-to-openai-o3-and-google-gemini-2-5-pro)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/deepseek-r1-0528/