DeepSeek

DeepSeek-R1

SIZE684B

54Quality

Reasoning

Downloads1.3M/mo

Likes14K

Language model from DeepSeek, 684B parameters.

Open weightsMIT473/1044

Drag to turn

DeepSeekTextPromo

DeepSeek-R1

Language model from DeepSeek, 684B parameters.

deepseek-ai/DeepSeek-R1

Type: Text
Quality: 54 · Top 46% on the Epoch Capabilities Index
Parameters: 684B (684,489,845,504)
Downloads: 1.3M in the last 30 days
Likes: 14K
Access to weights: Open download
On Hugging Face since: Jan 20, 2025
Takes in: Text
Puts out: Text
Access: Open weights
License: MIT
Rarity: Promo
Set number: 473/1044

Open on Hugging Face Quality 54 Where to run it 21 Race it 21 tok/s Meet its creature Battle MiniCPM5-2B

License read from the model’s Hugging Face card. Stats from DeepSeek’s official Hugging Face account, refreshed daily.

How good is it?

Public leaderboard scores for DeepSeek-R1, refreshed daily from Epoch AI and LMArena.

Top 46% of the 277 models on the Epoch Capabilities Index: #127.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Epoch Capabilities Index#127 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.139.0 index
LMArena Text#181 of 416
People compare two anonymous answers and vote for the better one.1,373 rating
LMArena Text · Coding#203 of 411
The text arena’s coding prompts only.1,371 rating
LMArena Text · Math#170 of 400
The text arena’s math prompts only.1,392 rating
LMArena Text · Creative writing#162 of 414
The text arena’s creative writing prompts only.1,354 rating

Benchmarks Epoch AI runs

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

20 providers sell DeepSeek-R1 through an API, and 1 Hugging Face host serves it. Prices are per million tokens, cheapest first.

CheapestNanoGPT$0.40 in · $1.70 out
Free to try1 provideriFlow
Fastest on Hugging FaceNovita21 tokens/s

API providers

Provider	Input	Output	Context
iFlowFree`deepseek-r1`	Free	Free	128K
NanoGPTCheapest paid`deepseek-r1`	$0.40	$1.70	128K
SiliconFlow`deepseek-ai/DeepSeek-R1`	$0.50	$2.18	164K
SiliconFlow (China)`deepseek-ai/DeepSeek-R1`	$0.50	$2.18	164K
D.Run (China)`public/deepseek-r1`	$0.55	$2.20	131K
Alibaba (China)`deepseek-r1`	$0.57	$2.29	131K
Eden AI`deepinfra/deepseek-ai/DeepSeek-R1`	$0.70	$2.40	164K
Novita AI`deepseek/deepseek-r1-turbo`	$0.70	$2.50	64K
Melious`deepseek-r1-0528`	$0.70	$2.78	164K
Amazon Bedrock`deepseek.r1-v1:0`	$1.35	$5.40	128K

Show 10 more providers

Provider	Input	Output	Context
Azure`deepseek-r1`	$1.35	$5.40	164K
Azure Cognitive Services`deepseek-r1`	$1.35	$5.40	164K
Merge Gateway`deepseek/deepseek-r1`	$1.35	$5.40	164K
Vercel AI Gateway`deepseek/deepseek-r1`	$1.35	$5.40	128K
Abacus`deepseek-ai/DeepSeek-R1`	$3.00	$7.00	128K
Together AI`deepseek-ai/DeepSeek-R1`	$3.00	$7.00	164K
IO.NET`deepseek-ai/DeepSeek-R1-0528`	$2.00	$8.75	128K
AnyAPI`deepseek/deepseek-r1`	—	—	1M
Qiniu`deepseek-r1`	—	—	128K
Snowflake Cortex`deepseek-r1`	—	—	128K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
NovitaTools	$0.70	$2.50	64K	21 tok/s	1.0s

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

DeepSeek-R1

DeepSeek-R1

How good is it?

Leaderboards

Benchmarks Epoch AI runs

Where to run it

API providers

Hugging Face Inference Providers

More from DeepSeek

DeepSeek V4.1 Flash 1017

DeepSeek-V4.1-Flash

DeepSeek-V4-Pro-0813

DeepSeek V4 Pro

DeepSeek-V4-Flash-0731

DeepSeek-V4-Flash-DSpark

DeepSeek-OCR-2

DeepSeek-V3.2