DeepSeek: DeepSeek V3.1 is DeepSeek's model, and its measured tokenizer sits in DeepSeek's own signature group alongside its sibling models. Measured models from StepFun carry the same vocabulary, which reads as reuse of DeepSeek's tokenizer line and questions nobody's authorship; they are listed under "Shares this fingerprint" below.
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Exact match with 1 other model | tk_869dc1cf |
| API surface | No other entry shares this exact contract | api_13422a94 |
| Context and output | 163,840 context · 32,768 max output | declared |
| Reasoning contract | Optional | declared |
| Serving providers observed | SiliconFlow, Google | measured 21 August 2026 |
Click a row to open the full comparison.
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 7 prompt tokens.
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
defaults: {}
Cite this page as the evidence record for DeepSeek: DeepSeek V3.1: 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.
