Back to Models
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
#129 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
16,000Reasoning Configuration
- Default
- Thinking on
- Turning thinking off
- Not possible (always thinks)
Data policy
- Prompt retention
- Unknown — we could not confirm
- Training
- Unknown — not declared
"Unknown" does not mean "safe". It means we could not confirm it.
Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.
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?
- #146 on the public arena's Japanese board (ELO 1,337). Ranks move as the leaderboard is updated.
Leaderboard
Text
russianELO: 1,382
#172CodingELO: 1,444
#166MathELO: 1,412
#143Creative WritingELO: 1,374
#153Instruction FollowingELO: 1,397
#152Hard PromptsELO: 1,419
#166Multi-TurnELO: 1,410
#154OverallELO: 1,398
#167JapaneseELO: 1,337
#146ChineseELO: 1,428
#164KoreanELO: 1,358
#129EnglishELO: 1,413
#165frenchELO: 1,391
#181germanELO: 1,399
#132spanishELO: 1,399
#155Rankings: LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, snapshot 2026-10-22; category names mapped and ratings rounded by FastMetal.