Are the weights open and can I run R1 0528 locally?

Yes, the weights are open and available on Hugging Face under deepseek-ai/DeepSeek-R1-0528. At 671B total parameters you will need substantial hardware to run the full model locally; a quantized version or a smaller distilled variant is more practical for most setups.

What does R1 0528 cost and what is the context window?

Via API it is priced at $0.50 per million input tokens and $2.15 per million output tokens, with a 163,840-token context window.

How is R1 0528 different from the original DeepSeek R1?

It is a post-training update focused on deeper reasoning: DeepSeek reports the model now uses roughly twice as many tokens per reasoning step, with meaningful gains on math and coding benchmarks and a lower hallucination rate, plus added function-calling support that was not benchmarked in the original.

R1 0528

4585°

#llm #deepseek #reasoning #math #coding #local

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

DeepSeek | 163,840 token context | $0.50/M input, $2.15/M output. 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...

Guides for this model

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

Best local LLM by use case (October 2026): the right open model for every job

How much VRAM do I actually need for local AI?

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

DeepSeek R1 0528 is a May 2025 update to DeepSeek's flagship reasoning model, built by DeepSeek. At 671B parameters with 37B active, it pushes noticeably harder on math, competitive coding and logic than the original R1, with DeepSeek citing benchmark gains across the board. Open weights and fully visible reasoning traces make it a serious option if you want a frontier-class reasoner you can actually inspect and run yourself.

Known for

Strong math performance, including large AIME 2025 accuracy gains over original R1.
Competitive coding results, with major improvements on LiveCodeBench and Aider-Polyglot.
Fully open reasoning tokens — you see the chain of thought, not just the answer.
Reduced hallucination rate and improved function calling versus the prior version.
Open weights available on Hugging Face for self-hosted deployment.

Watch out for

671B total parameters means running it locally demands serious hardware; most users will hit an API.
Context is 163,840 tokens — long, but falls short of the 200K threshold for a 'long context' label.
SimpleQA score dropped slightly from the original R1, so factual recall is not a clean win.

Best for

Prompts to try

Competitive math problem

Find all positive integers n such that n^2 + 1 divides n^3 + 7. Show every step of your reasoning, including how you rule out cases, and state the complete solution set with proof.

Debug a tricky function

Here is a Python function that is supposed to return the longest substring without repeating characters, but it sometimes returns the wrong length for strings with Unicode characters. Walk through what is wrong, explain why, and give a corrected version with a brief test. def longest_unique(s): seen = {} start = max_len = 0 for i, c in enumerate(s): if c in seen: start = seen[c] + 1 seen[c] = i max_len = max(max_len, i - start + 1) return max_len

Plan a multi-step agent

Design a minimal autonomous agent that monitors a directory for new CSV files, validates that each file has the required columns (date, amount, category), moves invalid files to a quarantine folder, and appends valid rows to a SQLite database. List the tools the agent needs, the decision logic at each step, and any failure modes worth handling.

Compare with

DeepSeek V4.1 Flash
Open-weights model
1,048,576 token context · $0.04/M input, $0.68/M output
DeepSeek V4 Flash 0731
Open-weights model
1,048,576 token context · $0.01/M input, $1.28/M output
DeepSeek V4 Flash 0423
Open-weights model
1,048,576 token context · $0.09/M input, $0.18/M output
DeepSeek V4 Pro 0813
Open-weights model
1,048,576 token context · $1.32/M input, $3.96/M output

More text models from deepseek

Questions people ask

Are the weights open and can I run R1 0528 locally?: Yes, the weights are open and available on Hugging Face under deepseek-ai/DeepSeek-R1-0528. At 671B total parameters you will need substantial hardware to run the full model locally; a quantized version or a smaller distilled variant is more practical for most setups.
What does R1 0528 cost and what is the context window?: Via API it is priced at $0.50 per million input tokens and $2.15 per million output tokens, with a 163,840-token context window.
How is R1 0528 different from the original DeepSeek R1?: It is a post-training update focused on deeper reasoning: DeepSeek reports the model now uses roughly twice as many tokens per reasoning step, with meaningful gains on math and coding benchmarks and a lower hallucination rate, plus added function-calling support that was not benchmarked in the original.

Captain's verdict
If you want a frontier reasoner with open weights and visible thinking, R1 0528 is the most capable version of DeepSeek's best model yet.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

AI Models for Image, Video & Text Generation

R1 0528 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm deepseek reasoning math coding local agents

Browse by Model Family