DeepSeek: R1 Distill Llama 70B is DeepSeek's model, and its measured tokenizer sits in DeepSeek's own signature group, shared with its sibling models and nobody else measured so far.
The mismatch was traced to the serving layer, not the label. The model's own repository tokenizer, run over the same 50 strings offline, is Llama 3's exactly (50 of 50, vocabulary 128,256), so the catalogue's Llama3 tag is right about the weights. The endpoint's reported token counts tell a different story: they match DeepSeek-V3's repository tokenizer on every string once the template boundary is folded, and the model's own tokenizer on only 18 of 50. The token accounting behind this endpoint uses a DeepSeek vocabulary the model does not read with, which sets what users are billed. Whether that is a billing-side tokenizer configuration or something else about the serving path cannot be established from token counts alone.
DeepSeek-R1-Distill-Llama-70B repository (config.json: vocab_size 128256, LlamaForCausalLM)DeepSeek-V3 repository (config.json: vocab_size 129280)
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Exact match with 1 other model | tk_869dc1cf |
| API surface | No other entry shares this exact contract | api_28524539 |
| Context and output | 8,192 context · 8,192 max output | declared |
| Reasoning contract | Optional | declared |
| Serving providers observed | Novita | 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: 3 prompt tokens.
DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyseedstoptemperaturetop_ktop_p
defaults: {}
Cite this page as the evidence record for DeepSeek: R1 Distill Llama 70B: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.
