Are the weights open and can I run R1 locally?

Yes — DeepSeek R1 is MIT-licensed with weights on Hugging Face, so you can download and run it locally, though the full 671B model requires substantial hardware; the six distilled variants (down to 1.5B) are far more practical for local use.

What does it cost and what is the context window?

Via the API it is priced at $0.70 per million input tokens and $2.50 per million output tokens, with a 64,000-token context window.

How does R1 differ from DeepSeek's other models?

R1 is DeepSeek's reasoning-focused model, trained with large-scale reinforcement learning to produce explicit chain-of-thought; it targets math, code, and complex reasoning rather than general-purpose chat, and it exposes its reasoning tokens rather than hiding them.

R1

1660°

#llm #deepseek #reasoning #math #coding #research

Runs on Graydient

Run this model

Offers / Ads

Easy Creator (Prism) Web

Unlimited · flat fee

Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.

PirateDiffusion Telegram

Unlimited · flat fee

Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.

Pro studio (SpyGlass) Web

Unlimited · flat fee

Best for power users. Full control over models, settings and workflows in a browser studio.

Discord bot (Vector)

Unlimited · flat fee

Best for communities. Add it to your own server and run any workflow from a channel.

Unified Editor Web

Unlimited · flat fee

One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.

OpenRouter Terminal / API

Pay per token

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

Local apps

Requires setup

Set up local programs if your computer has capable hardware.

ModelDuel Web

Pay per use

Generate the same prompt on up to 50 checkpoint/base models at a time.

Rent a GPU on the cloud

Graydient Cloud GPU

Unlimited · flat fee

Flat fee, unlimited use. This model installs with one click.

RunPod Cloud GPU

Charged by the minute

Rent a GPU by the minute and set the model up yourself.

Guides for this model

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

DeepSeek | 64,000 token context | $0.70/M input, $2.50/M output. DeepSeek R1 is here: Performance on par with 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 & technical reportOpens in new tab. MIT licensed: Distill & commercialize freely!

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

DeepSeek R1 is a 671-billion-parameter mixture-of-experts reasoning model from DeepSeek, trained primarily through reinforcement learning rather than supervised fine-tuning. It matches OpenAI o1 on math, code, and reasoning tasks, while publishing its chain-of-thought tokens openly — something o1 does not do. MIT-licensed and open-weights, it suits researchers, developers, and anyone who wants a frontier-class reasoner they can actually inspect, distill, or deploy commercially.

Known for

Reasoning performance comparable to OpenAI o1 on math, code, and logic tasks
Fully visible chain-of-thought tokens — the reasoning process is not hidden
MIT licence: distill, fine-tune, and commercialize without restriction
Six smaller distilled models released alongside, down to 1.5B parameters
RL-trained reasoning that emerged self-verification and reflection behaviors

Watch out for

671B total parameters: running it locally demands serious hardware; most users will hit the API.
64,000-token context window is shorter than several rivals at this performance tier.
The predecessor R1-Zero showed language-mixing and repetition issues; R1 improves this but review the usage recommendations before deploying.

Best for

Prompts to try

Proof by contradiction

Prove that the square root of 2 is irrational. Show every step of your reasoning, flag any assumption you make, and check your own argument for gaps before giving a final answer.

Debug a tricky function

Here is a Python function that is supposed to return the longest substring without repeating characters, but it returns wrong results on some inputs. Walk through the logic step by step, identify the bug, explain why it fails, and give a corrected version with a brief explanation. def longest_unique(s): seen = {} start = 0 best = '' for i, c in enumerate(s): if c in seen: start = seen[c] seen[c] = i if i - start + 1 > len(best): best = s[start:i+1] return best

Plan under constraints

A small team of three engineers must migrate a live production database to a new schema with zero downtime. The database has 50 million rows and the application cannot be taken offline. Think through the risks, list the steps in order, and explain the reasoning behind each decision before giving your final migration plan.

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 locally?: Yes — DeepSeek R1 is MIT-licensed with weights on Hugging Face, so you can download and run it locally, though the full 671B model requires substantial hardware; the six distilled variants (down to 1.5B) are far more practical for local use.
What does it cost and what is the context window?: Via the API it is priced at $0.70 per million input tokens and $2.50 per million output tokens, with a 64,000-token context window.
How does R1 differ from DeepSeek's other models?: R1 is DeepSeek's reasoning-focused model, trained with large-scale reinforcement learning to produce explicit chain-of-thought; it targets math, code, and complex reasoning rather than general-purpose chat, and it exposes its reasoning tokens rather than hiding them.

Captain's verdict
The most significant open-weights reasoning model released so far: frontier performance, MIT licence, and nothing hidden in the thinking process.

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

Qwen3.5 Plus 2026 02 15

AI Models for Image, Video & Text Generation

R1 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, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.

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

Browse by Model Family