Why high: an exact fingerprint shared with 8 models that declare the same family, without a second signal of a different kind yet.
Meta: Llama 3.3 70B Instruct is Meta's model. Its measured tokenizer sits with the Llama3 group, which is evidence that it builds on the Llama3 tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Meta's authorship of the model itself.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Counts every one of the 50 test strings exactly like 8 other models | tk_6588ed5b |
| How its API is set up | A combination of settings no other listing in the catalogue uses | api_607fdf1c |
| How much it can read and write | Reads up to 131,072 tokens at once, writes up to 16,384 | its own listing |
| Who served our requests | DeepInfra | we measured it, 5 October 2026 |
| Measured twice | The 5 October 2026 reading agreed with the 21 August 2026 reading on every one of the 50 strings clean in both: the tokenizer behind this name held. | 50/50 agree |
Click a row to open the full comparison.
We sent Meta: Llama 3.3 70B Instruct 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: 10 prompt tokens.
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
Supported parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
defaults: {}
