StepFun: Step 3.7 Flash is StepFun's model. Its measured tokenizer sits with the DeepSeek group, which is evidence that it builds on the DeepSeek tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against StepFun's authorship of the model itself.
As with Step 3.5 Flash: StepFun's own Step-3 repository ships a tokenizer behaviourally identical to DeepSeek-V3's over all 50 strings, and this endpoint counts the same way. Its place in the DeepSeek signature group is genuine lineage reuse by StepFun.
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Exact match with 9 other models | tk_73c4f0dc |
| API surface | No other entry shares this exact contract | api_941e54b9 |
| Context and output | 262,144 context · 256,000 max output | declared |
| Reasoning contract | Mandatory · efforts high, medium, low · default medium | declared |
| Serving providers observed | DeepInfra | 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: 12 prompt tokens.
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_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 StepFun: Step 3.7 Flash: 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.
