Why high: an exact fingerprint shared with 2 models that declare the same family, without a second signal of a different kind yet.
DeepSeek: DeepSeek V3 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.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Counts every one of the 50 test strings exactly like 2 other models | tk_869dc1cf |
| How its API is set up | A combination of settings no other listing in the catalogue uses | api_df1ebd04 |
| How much it can read and write | Reads up to 163,840 tokens at once, writes up to 16,000 | its own listing |
| Who served our requests | DeepInfra | we measured it, 5 October 2026 |
| Measured twice | Between 21 August 2026 and 5 October 2026, 2 of 50 strings moved by exactly one token, the mark of a changed serving template in front of the same vocabulary. | 48/50 agree |
Click a row to open the full comparison.
We sent DeepSeek: DeepSeek V3 fifty short pieces of text and recorded what each one cost it in tokens. The bars below are those costs. Two models built on the same tokenizer produce the same bars; a model built on a different one produces a different set, which is what makes this a fingerprint.
Overhead subtracted: 3 prompt tokens.
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...
Supported parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
defaults: {}
