Back to Models
deepseek logo
deepseek/deepseek-r1
Not Available

R1

DeepSeek R1 is here: 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 in an inference pass. Fully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120). MIT licensed: Distill & commercialize freely!

1/20/2025
64,000 tokens
#110 Text (Korean)

Specifications

Modalities

Input
text
Output
text

Supported Parameters

frequency_penalty
include_reasoning
max_tokens
presence_penalty
reasoning
repetition_penalty
seed
stop
temperature
tool_choice
tools
top_k
top_p

Max Output Tokens

16,000

Reasoning Configuration

Default
Thinking on
Turning thinking off
Not possible (always thinks)

How to control thinking, and what it costs

Frequently asked questions

Is R1 available on FastMetal?
Not at the moment. DeepSeek V4.1 Flash, from the same lab, is available on the FastMetal API today.
What is the context window of R1?
64,000 tokens, shared between the prompt and the response.
How does R1 rank?
#126 on the public arena's Japanese board (ELO 1,338). Ranks move as the leaderboard is updated.

Leaderboard

Text
OverallELO: 1,398
#149
JapaneseELO: 1,338
#126
ChineseELO: 1,429
#148
KoreanELO: 1,358
#110
EnglishELO: 1,413
#148
frenchELO: 1,390
#159
germanELO: 1,398
#115
spanishELO: 1,399
#131
russianELO: 1,381
#157
MathELO: 1,412
#124
CodingELO: 1,444
#147
Creative WritingELO: 1,374
#138
Instruction FollowingELO: 1,397
#137
Hard PromptsELO: 1,418
#148
Multi-TurnELO: 1,410
#135