DeepSeek: R1
deepseek/deepseek-r1 · DeepSeekNot yet established- Declared family
- DeepSeek
- Evidence confidence
- Unknown
- Declared tokenizer tag
- DeepSeek
- Entered catalogue
- 20 January 2025
- Last tested
- Not yet measured
- Measurement
- Awaiting measurement
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Not measured | – |
| API surface | No other entry shares this exact contract | api_50c80d14 |
| Context and output | 64,000 context · 16,000 max output | declared |
| Reasoning contract | Mandatory | declared |
| Serving providers observed | None recorded yet | – |
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....
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}
Cite this page as the evidence record for DeepSeek: R1: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.